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

    Neuronpedia

    INDEX
    Explanations

    fracturing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     piracy
    -0.07
    owych
    -0.07
    irket
    -0.06
     моз
    -0.06
    (arc
    -0.06
    .avatar
    -0.06
    재
    -0.06
    раста
    -0.06
     götür
    -0.06
    961
    -0.06
    POSITIVE LOGITS
    *****
↵
    0.07
       ↵↵
    0.06
    The
    0.06
    <>();
↵
    0.06
     Комп
    0.06
    _REGION
    0.06
    ="${
    0.06
    409
    0.06
    ighbor
    0.06
    ModelProperty
    0.06
    Act Density 0.001%

    No Known Activations