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

    Neuronpedia

    INDEX
    Explanations

    levels

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numeric values (probability or weight scores).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ored
    -0.07
    Award
    -0.06
    Hand
    -0.06
    ampion
    -0.06
     Jones
    -0.06
    leads
    -0.06
     Robinson
    -0.06
     Young
    -0.06
    Wrong
    -0.06
     lion
    -0.06
    POSITIVE LOGITS
    :result
    0.07
     المت
    0.06
    Bounds
    0.06
     remake
    0.06
    _pagination
    0.06
    sep
    0.06
    _snap
    0.06
    เฉล
    0.06
    ━�
    0.06
     pocit
    0.06
    Act Density 0.353%

    No Known Activations