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

    Neuronpedia

    INDEX
    Explanations

    illegal activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Product
    -0.07
    _curve
    -0.07
    example
    -0.07
    Ale
    -0.06
    Tabla
    -0.06
    _proj
    -0.06
    Scene
    -0.06
    άλι
    -0.06
    латы
    -0.06
     canopy
    -0.06
    POSITIVE LOGITS
     fucked
    0.07
     mashed
    0.07
    .Gray
    0.06
     bat
    0.06
     Scala
    0.06
     clearer
    0.06
     methodologies
    0.06
    847
    0.06
    405
    0.06
    prec
    0.06
    Act Density 0.074%

    No Known Activations