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

    Neuronpedia

    INDEX
    Explanations

    -per

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “pay‐per‐view” (PPV) events or related pay‐per‐view terminology.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Πο
    -0.07
     Γου
    -0.07
    "G
    -0.07
    ificar
    -0.07
     bla
    -0.07
    لاة
    -0.06
    /be
    -0.06
    "D
    -0.06
    öst
    -0.06
    買
    -0.06
    POSITIVE LOGITS
    Serializer
    0.07
     CLIENT
    0.07
    _PIN
    0.06
     strictly
    0.06
     Helper
    0.06
     nền
    0.06
     hail
    0.06
     interpreter
    0.06
    _serializer
    0.06
     attn
    0.06
    Act Density 0.005%

    No Known Activations