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

    Neuronpedia

    INDEX
    Explanations

    Disambiguation/Occupations/Nationalities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hazards
    -0.07
     Nordic
    -0.07
    ción
    -0.06
     reductions
    -0.06
     devoid
    -0.06
    _build
    -0.06
    ritz
    -0.06
    CMP
    -0.06
     GOODS
    -0.06
     KA
    -0.06
    POSITIVE LOGITS
    ĐT
    0.07
    Glyph
    0.07
    Gun
    0.06
     Gun
    0.06
    _SAMPLES
    0.06
    Panel
    0.06
    _tcb
    0.06
    .Getter
    0.06
     bills
    0.06
    .shadow
    0.06
    Act Density 0.149%

    No Known Activations