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

    Neuronpedia

    INDEX
    Explanations

    written

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frees
    -0.08
    בוה
    -0.08
     nieruchomo
    -0.07
    תוכ
    -0.07
    ⌊
    -0.07
    Gene
    -0.07
     Serialize
    -0.07
    Wat
    -0.07
     (~(
    -0.07
    油气
    -0.07
    POSITIVE LOGITS
    PCA
    0.07
    conexion
    0.07
    .product
    0.07
     decided
    0.07
    .tintColor
    0.07
    _equal
    0.07
    移民
    0.07
    blue
    0.07
    /security
    0.07
    roperty
    0.07
    Act Density 0.000%

    No Known Activations