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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and licensing terms related to software

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

    Copyright or licensing statements

    np_acts-logits-general · gemini-2.0-flash

    copyright and license text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ±
    -0.95
     ±
    -0.92
     +/-
    -0.78
     (±
    -0.71
     +-
    -0.70
    DockStyle
    -0.67
     ± 
    -0.67
    +/-
    -0.59
    kuuta
    -0.59
    +-
    -0.57
    POSITIVE LOGITS
    toed
    0.55
     متعلقه
    0.54
     kasarigan
    0.52
    ORAGE
    0.51
    ]<<"
    0.50
    бля
    0.49
     notice
    0.49
     $__
    0.48
     Kos
    0.47
    AndPassword
    0.47
    Act Density 0.294%

    No Known Activations