Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical terms and expressions related to properties of invertibility and singularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or formal/technical writing

    np_acts-logits-general · gemini-2.0-flash

    openness and invertibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stationary
    -0.51
    shutdown
    -0.51
    +#+#
    -0.49
     stabili
    -0.48
    穩定
    -0.48
     stabilizing
    -0.47
     calmed
    -0.47
     stabilized
    -0.45
     nocturna
    -0.45
     ndani
    -0.45
    POSITIVE LOGITS
    開放
    0.49
     للاسماء
    0.47
     Clear
    0.47
    Clear
    0.46
     open
    0.45
     Open
    0.45
     openness
    0.44
     Clearance
    0.44
     OPEN
    0.43
    quiao
    0.42
    Act Density 0.928%

    No Known Activations