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

    Neuronpedia

    INDEX
    Explanations

    Questions and instructions

    np_max-act · gemini-2.0-flash

    This neuron is effectively “dead” — it never activates (all token activations remain zero).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    يدي
    -0.07
    lung
    -0.06
    acting
    -0.06
     Re
    -0.06
     Vince
    -0.06
     via
    -0.06
     Admission
    -0.06
     Фед
    -0.06
    BackPressed
    -0.06
     Blender
    -0.06
    POSITIVE LOGITS
    -have
    0.06
     Carlton
    0.06
     sein
    0.06
    (rule
    0.06
     Fail
    0.06
    wave
    0.06
    ้้
    0.06
     λα
    0.06
    ("'",
    0.06
    Logs
    0.06
    Act Density 0.037%

    No Known Activations