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

    Neuronpedia

    INDEX
    Explanations

    Code/configuration files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Input
    -0.08
     Console
    -0.07
    buster
    -0.07
     worms
    -0.07
     культури
    -0.07
     thread
    -0.06
    みたい
    -0.06
    َ
    -0.06
    yro
    -0.06
    input
    -0.06
    POSITIVE LOGITS
    溫
    0.06
     ΑΝ
    0.06
     sourceMapping
    0.06
    ['
    0.06
    ,:),
    0.06
     Chili
    0.06
    ,’’
    0.06
     antagonist
    0.06
     �
    0.06
     mare
    0.06
    Act Density 0.004%

    No Known Activations