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

    Neuronpedia

    INDEX
    Explanations

    Absence or negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ementia
    -0.07
     Paradise
    -0.07
    еление
    -0.06
    ("="
    -0.06
    _METADATA
    -0.06
    _inverse
    -0.06
     захисту
    -0.06
     cone
    -0.06
    defs
    -0.06
    護
    -0.06
    POSITIVE LOGITS
     divider
    0.07
    CAM
    0.07
     Cele
    0.06
     cliente
    0.06
    -width
    0.06
     تن
    0.06
     prod
    0.06
     brave
    0.06
     mine
    0.06
     trem
    0.06
    Act Density 0.012%

    No Known Activations