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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Selected
    -0.07
    Filename
    -0.06
     Able
    -0.06
     forgive
    -0.06
    晨
    -0.06
    _information
    -0.06
    Cre
    -0.06
    Informe
    -0.06
     Granny
    -0.06
    183
    -0.05
    POSITIVE LOGITS
    екту
    0.07
    声
    0.07
    -pe
    0.06
    english
    0.06
    ual
    0.06
    Assets
    0.06
     �
    0.06
    -regexp
    0.06
    MR
    0.06
    汉
    0.06
    Act Density 0.051%

    No Known Activations