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

    Neuronpedia

    INDEX
    Explanations

    relied

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ighter
    -0.07
    зем
    -0.07
    ительным
    -0.07
    ambda
    -0.06
     confess
    -0.06
    _diff
    -0.06
    ющее
    -0.06
     bew
    -0.06
     prohib
    -0.06
     conferred
    -0.06
    POSITIVE LOGITS
     Savage
    0.07
     عامل
    0.07
    อนด
    0.07
    endez
    0.06
     UIBarButtonItem
    0.06
    _decision
    0.06
    Texas
    0.06
    _COUNT
    0.06
     Fancy
    0.06
    άβ
    0.06
    Act Density 0.002%

    No Known Activations