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

    Neuronpedia

    INDEX
    Explanations

    _view

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    声を
    -0.07
    Paths
    -0.06
     primes
    -0.06
    Measurement
    -0.06
     doktor
    -0.06
    KR
    -0.06
    لا
    -0.06
    250
    -0.06
    Metric
    -0.06
    inscription
    -0.06
    POSITIVE LOGITS
    -fired
    0.07
     kavram
    0.07
     convicted
    0.06
     Voy
    0.06
     thin
    0.06
     oversees
    0.06
     dive
    0.06
     deficient
    0.06
    υγ
    0.06
     Six
    0.06
    Act Density 0.004%

    No Known Activations