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

    Neuronpedia

    INDEX
    Explanations

    Geographical locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Const
    -0.07
    instant
    -0.07
     marg
    -0.06
    .for
    -0.06
    /browser
    -0.06
    卬
    -0.06
    肺炎
    -0.06
    ڱ
    -0.06
    לג
    -0.06
    -binary
    -0.06
    POSITIVE LOGITS
    叙述
    0.07
     newsletters
    0.07
     NEO
    0.07
    下达
    0.07
     rehab
    0.07
     Clo
    0.06
    macros
    0.06
     Gespräch
    0.06
     warfare
    0.06
    ?=
    0.06
    Act Density 0.080%

    No Known Activations