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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries related to possibility or necessity

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

    Questions and uncertainty

    np_acts-logits-general · gemini-2.0-flash

    questions about possibility or necessity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neither
    -0.94
    neither
    -0.90
    Neither
    -0.83
     Neither
    -0.82
     nowhere
    -0.77
    almost
    -0.75
     rarely
    -0.73
     nobody
    -0.72
    very
    -0.71
     none
    -0.71
    POSITIVE LOGITS
     ever
    1.31
     jemals
    1.06
     denn
    1.06
     really
    1.00
     perchance
    0.96
     any
    0.96
     acaso
    0.95
     überhaupt
    0.92
     still
    0.92
     Really
    0.91
    Act Density 0.437%

    No Known Activations