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

    Neuronpedia

    INDEX
    Explanations

    say "itis"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acheter
    -0.07
     layout
    -0.06
     hashtable
    -0.06
     everything
    -0.06
    ToRemove
    -0.06
    ++)↵
    -0.06
     abril
    -0.06
     Superman
    -0.06
     табли
    -0.06
     passenger
    -0.06
    POSITIVE LOGITS
     indul
    0.06
    ussed
    0.06
    �数
    0.06
     وزن
    0.06
    воз
    0.06
    iasm
    0.06
     verdict
    0.06
    @Web
    0.06
    BAL
    0.06
    oshi
    0.06
    Act Density 0.044%

    No Known Activations