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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act · gemini-2.0-flash

    The neuron is primarily activated by the token “what.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -files
    -0.07
    _fig
    -0.07
    apus
    -0.07
    -shift
    -0.06
     floppy
    -0.06
    thew
    -0.06
     Chelsea
    -0.06
    -white
    -0.06
    -wrap
    -0.06
     bölg
    -0.06
    POSITIVE LOGITS
    _GROUPS
    0.07
    ्
    0.07
    getAll
    0.06
     LAS
    0.06
     Definitely
    0.06
    .Millisecond
    0.06
    赖
    0.06
    (vector
    0.06
     Controls
    0.06
     Intercept
    0.06
    Act Density 0.011%

    No Known Activations