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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literal tokens (e.g. integer or floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .anchor
    -0.08
     getMax
    -0.07
     Layers
    -0.07
     zpracování
    -0.07
     Grupo
    -0.06
    .rar
    -0.06
    (unique
    -0.06
    ↵      ↵
    -0.06
     Seth
    -0.06
    -txt
    -0.06
    POSITIVE LOGITS
     immigration
    0.07
    oked
    0.06
     skirt
    0.06
    ~,
    0.06
    Ñ
    0.06
     mean
    0.06
     flowing
    0.06
    ками
    0.06
    alore
    0.06
    Who
    0.06
    Act Density 0.048%

    No Known Activations