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

    Neuronpedia

    INDEX
    Explanations

    Current working directory commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gras
    -0.07
    еси
    -0.06
     dispos
    -0.06
     distinction
    -0.06
    .mas
    -0.06
    .Flags
    -0.06
    wire
    -0.06
     Amsterdam
    -0.06
    ≦
    -0.06
    compose
    -0.06
    POSITIVE LOGITS
     Environment
    0.07
     wives
    0.07
     Lawn
    0.07
    ido
    0.07
     Prep
    0.07
     pwd
    0.07
    (of
    0.06
     Daniels
    0.06
     起
    0.06
    饮
    0.06
    Act Density 0.003%

    No Known Activations