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

    Neuronpedia

    INDEX
    Explanations

    Code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    from
    -0.07
    begin
    -0.06
    Answer
    -0.06
     fmt
    -0.06
    Animated
    -0.06
    ishment
    -0.06
    [y
    -0.06
    ament
    -0.06
    .syn
    -0.06
     gin
    -0.06
    POSITIVE LOGITS
     truncated
    0.07
    ButtonText
    0.07
    MISS
    0.07
     ника
    0.07
     LIMITED
    0.07
    ी।
    0.06
     tarif
    0.06
    0.06
     obligations
    0.06
     DA
    0.06
    Act Density 0.013%

    No Known Activations