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

    Neuronpedia

    INDEX
    Explanations

    V

    np_max-act · gemini-2.0-flash

    This neuron detects numeric measurement tokens—particularly floating-point values (decimal numbers) appearing in the experimental data.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cha
    -0.08
    yster
    -0.07
    raid
    -0.07
     dim
    -0.06
     系
    -0.06
     queens
    -0.06
     quarantine
    -0.06
    ared
    -0.06
     unprecedented
    -0.06
     дор
    -0.06
    POSITIVE LOGITS
     bás
    0.06
    (Sprite
    0.06
    (svg
    0.06
     estud
    0.06
     대상
    0.06
    .drawImage
    0.06
     onResponse
    0.06
    (editor
    0.06
    있
    0.06
     nejvyšší
    0.05
    Act Density 0.000%

    No Known Activations