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

    Neuronpedia

    INDEX
    Explanations

    general sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gang
    -0.07
     identifying
    -0.07
    ,test
    -0.06
     murm
    -0.06
    fcc
    -0.06
     flags
    -0.06
     DISABLE
    -0.06
     projectId
    -0.06
     Роб
    -0.06
    刷
    -0.06
    POSITIVE LOGITS
    NSS
    0.07
     Locke
    0.07
    (LL
    0.06
    .INTER
    0.06
     HF
    0.06
    盛
    0.06
    ylv
    0.06
    /item
    0.06
     possess
    0.06
    ří
    0.06
    Act Density 0.073%

    No Known Activations