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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bond
    -0.06
    必须
    -0.06
     Initial
    -0.06
    政
    -0.06
     тран
    -0.06
     cười
    -0.06
     Calls
    -0.06
     Secretary
    -0.06
     선
    -0.06
    term
    -0.06
    POSITIVE LOGITS
    /license
    0.07
    memcmp
    0.07
    cstdio
    0.07
    []=$
    0.06
     plurality
    0.06
     GLint
    0.06
    (poly
    0.06
    ',//
    0.06
    Exist
    0.06
    ~,
    0.06
    Act Density 0.008%

    No Known Activations