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

    Neuronpedia

    INDEX
    Explanations

    assistant/technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EntityType
    -0.08
    (np
    -0.07
    income
    -0.07
    .Office
    -0.07
     rp
    -0.07
    cak
    -0.07
    .=
    -0.07
     MVP
    -0.06
     -----↵
    -0.06
    "',
    -0.06
    POSITIVE LOGITS
     Crushing
    0.07
     colomb
    0.07
    焼
    0.06
     quán
    0.06
     compartir
    0.06
     lake
    0.06
     Searching
    0.06
    마
    0.06
     الحي
    0.06
     searches
    0.06
    Act Density 0.062%

    No Known Activations