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

    Neuronpedia

    INDEX
    Explanations

    Open

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shepherd
    -0.06
    .vector
    -0.06
    ),↵
    -0.06
    Technical
    -0.06
     mathematical
    -0.06
    宿
    -0.06
     postponed
    -0.06
     P
    -0.06
    experimental
    -0.06
     contador
    -0.06
    POSITIVE LOGITS
     samozřejmě
    0.07
     disproportionately
    0.07
    vice
    0.06
    Inside
    0.06
    _entities
    0.06
     jal
    0.06
    istrib
    0.06
    rupted
    0.06
    没有
    0.06
    UED
    0.06
    Act Density 0.036%

    No Known Activations