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

    Neuronpedia

    INDEX
    Explanations

    add

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preserve
    -0.07
     Normalize
    -0.07
     reserve
    -0.07
    券
    -0.07
     owning
    -0.06
    ứa
    -0.06
    액
    -0.06
    inction
    -0.06
    .exit
    -0.06
    itic
    -0.06
    POSITIVE LOGITS
     celkem
    0.07
     kli
    0.07
     Addition
    0.06
     sexdate
    0.06
     MLM
    0.06
     cowork
    0.06
    asters
    0.06
     Adler
    0.06
    slu
    0.06
    .setter
    0.06
    Act Density 0.022%

    No Known Activations