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

    Neuronpedia

    INDEX
    Explanations

    topics related to social issues and movements

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

    "From" followed by a noun and "to"

    np_acts-logits-general · gemini-2.0-flash

    ranges or sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.61
    AutoScaleMode
    -0.60
    uttavia
    -0.58
    ]--;
    -0.56
     Bioaccumulative
    -0.56
    __":
    -0.56
    CONSIN
    -0.53
     autrement
    -0.53
    ştir
    -0.53
     {}".
    -0.53
    POSITIVE LOGITS
     to
    1.65
    到
    1.11
     گرفته
    1.08
     đến
    1.05
     hasta
    0.98
     ועד
    0.98
     through
    0.97
     till
    0.93
     pasando
    0.92
     until
    0.92
    Act Density 0.249%

    No Known Activations