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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -million
    -0.07
     hơi
    -0.06
    flow
    -0.06
    -common
    -0.06
    .getDay
    -0.06
     Uns
    -0.06
     Dear
    -0.06
    icipant
    -0.06
     accomplish
    -0.06
     Belle
    -0.06
    POSITIVE LOGITS
     кри
    0.06
    _Tick
    0.06
    _erase
    0.06
    herence
    0.06
    .backup
    0.06
     harmless
    0.06
    ','=
    0.06
    Τ
    0.05
     schöne
    0.05
    ції
    0.05
    Act Density 0.021%

    No Known Activations