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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -cal
    -0.07
    انية
    -0.07
    _surf
    -0.07
    _some
    -0.07
    NORMAL
    -0.07
    ятся
    -0.07
    idata
    -0.06
    _he
    -0.06
    lapping
    -0.06
    cheduling
    -0.06
    POSITIVE LOGITS
    *j
    0.06
    *out
    0.06
    .Parent
    0.06
    .:.:
    0.06
    、
    0.06
    Yep
    0.06
     MMA
    0.06
     relieve
    0.06
    MB
    0.06
     myths
    0.06
    Act Density 0.041%

    No Known Activations