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

    Neuronpedia

    INDEX
    Explanations

    mechanical components and their interactions within machines

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

    Round, elongated objects

    np_acts-logits-general · gemini-2.0-flash

    long linear objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓘ
    -0.53
    Tembelea
    -0.50
    Smarty
    -0.47
    ITERIA
    -0.47
    BlockSize
    -0.46
    ArgumentParser
    -0.46
    atory
    -0.45
     bords
    -0.45
    aien
    -0.45
    batore
    -0.44
    POSITIVE LOGITS
     lengths
    1.09
     length
    1.07
     Length
    0.95
     lenght
    0.91
    length
    0.91
    Length
    0.86
     LENGTH
    0.83
    lengths
    0.74
     lengte
    0.73
     longueur
    0.73
    Act Density 0.659%

    No Known Activations