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

    Neuronpedia

    INDEX
    Explanations

    small

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stores
    -0.08
    Insensitive
    -0.08
    _DOWN
    -0.07
     most
    -0.07
    ready
    -0.07
     freshwater
    -0.07
     contracts
    -0.07
     Keeper
    -0.06
    Snake
    -0.06
    pop
    -0.06
    POSITIVE LOGITS
    .ColumnName
    0.06
     kleine
    0.06
     deine
    0.06
     látky
    0.06
    poke
    0.06
     llen
    0.06
    ψε
    0.06
     움
    0.06
    Compiler
    0.06
     calmly
    0.06
    Act Density 0.010%

    No Known Activations