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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     romance
    -0.07
    xbb
    -0.07
    ama
    -0.06
     NOR
    -0.06
     devil
    -0.06
     hace
    -0.06
    _cached
    -0.06
    lington
    -0.06
    connecting
    -0.06
    ्डल
    -0.06
    POSITIVE LOGITS
    .EXP
    0.07
     archive
    0.06
     seçim
    0.06
     exponentially
    0.06
    inke
    0.06
     zeros
    0.06
     dealloc
    0.06
    -range
    0.06
    .must
    0.06
     performing
    0.05
    Act Density 0.000%

    No Known Activations