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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Forums
    -0.08
     pillars
    -0.07
     MUCH
    -0.07
    ’s
    -0.07
    sons
    -0.07
    gency
    -0.07
    ัฒนา
    -0.07
     GTA
    -0.07
    's
    -0.07
    SOR
    -0.06
    POSITIVE LOGITS
     presumed
    0.07
    686
    0.07
     случай
    0.06
     �
    0.06
    料
    0.06
    opath
    0.06
    رسی
    0.06
    Req
    0.06
    .per
    0.06
    ocard
    0.06
    Act Density 0.042%

    No Known Activations