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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron detects numeric ranges expressed with hyphens (e.g., “1500-2000”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ็นต
    -0.07
     آب
    -0.07
     compensated
    -0.06
     SIL
    -0.06
     Hand
    -0.06
     adds
    -0.06
     پیک
    -0.06
     turns
    -0.06
     организм
    -0.06
     Floors
    -0.06
    POSITIVE LOGITS
    .descripcion
    0.07
     العربية
    0.06
     insight
    0.06
    .SetString
    0.06
    데
    0.06
     retiring
    0.06
    Pose
    0.06
     (~
    0.06
    Ont
    0.06
    _SC
    0.06
    Act Density 0.005%

    No Known Activations