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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash

    The neuron fires on the Java keyword “public,” detecting public declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    DEPTH
    -0.07
    -valu
    -0.07
    Ax
    -0.06
     ули
    -0.06
    253
    -0.06
     rotational
    -0.06
     graft
    -0.06
     seeding
    -0.06
     deterrent
    -0.06
     devil
    -0.06
    POSITIVE LOGITS
    dbc
    0.07
     inflamm
    0.07
    .*,
    0.07
    ów
    0.07
     stato
    0.07
    illian
    0.06
    在
    0.06
     happ
    0.06
    ()),↵
    0.06
    소
    0.06
    Act Density 0.002%

    No Known Activations