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

    Neuronpedia

    INDEX
    Explanations

    Abilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CAT
    -0.07
    ampton
    -0.07
    rido
    -0.07
    _sources
    -0.06
     backwards
    -0.06
    Official
    -0.06
     newPassword
    -0.06
     AK
    -0.06
    .ButterKnife
    -0.06
    asses
    -0.06
    POSITIVE LOGITS
    .chk
    0.07
     statist
    0.07
    veled
    0.07
     Winner
    0.07
     favor
    0.07
     çık
    0.06
     remind
    0.06
    標
    0.06
     SAME
    0.06
    _LEVEL
    0.06
    Act Density 0.004%

    No Known Activations