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

    Neuronpedia

    INDEX
    Explanations

    binary

    np_max-act · gemini-2.0-flash

    This neuron detects references to binary response variables and their numeric encodings (e.g. “binary,” “response,” “ones,” “zeros,” “data”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    哥
    -0.07
    akistan
    -0.07
    ==="
    -0.07
    OptionsItemSelected
    -0.06
    _venta
    -0.06
    _IN
    -0.06
     ErrorCode
    -0.06
    .usuario
    -0.06
     Hut
    -0.06
     ukon
    -0.06
    POSITIVE LOGITS
    .Surface
    0.06
     yoktu
    0.06
    _break
    0.06
    prime
    0.06
    NSDate
    0.06
     kterého
    0.06
     -,
    0.06
    _NEED
    0.06
    _PED
    0.06
    ิตภ
    0.06
    Act Density 0.004%

    No Known Activations