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

    Neuronpedia

    INDEX
    Explanations

    request

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens and figures (e.g. digits, monetary amounts, percentages).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Coding
    -0.06
     hearings
    -0.06
    Observ
    -0.06
     invention
    -0.06
    ru
    -0.06
     boring
    -0.06
     Address
    -0.06
    션
    -0.06
    Radio
    -0.06
     always
    -0.06
    POSITIVE LOGITS
    .visitInsn
    0.06
     heightened
    0.06
     notifyDataSetChanged
    0.06
    initializer
    0.06
     -=
    0.06
    -normal
    0.06
     sideways
    0.06
     floppy
    0.06
     ihre
    0.06
    .MoveNext
    0.06
    Act Density 0.009%

    No Known Activations