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

    Neuronpedia

    INDEX
    Explanations

    *w

    np_max-act · gemini-2.0-flash

    This neuron activates on Greek‐letter symbols (e.g. “ψ” in absorption‐correction entries).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    obuf
    -0.06
    -unit
    -0.06
     silver
    -0.06
    líb
    -0.06
     çevr
    -0.06
    (visible
    -0.06
    -ui
    -0.06
    采购
    -0.06
     Ub
    -0.06
     styl
    -0.06
    POSITIVE LOGITS
     nouvelles
    0.06
    COOKIE
    0.06
    альным
    0.06
    /component
    0.06
    =path
    0.06
    athlon
    0.06
     İş
    0.06
    /a
    0.06
    　　　　　　　　　　　　　　　　
    0.06
     lowers
    0.06
    Act Density 0.000%

    No Known Activations