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

    Neuronpedia

    INDEX
    Explanations

    photography

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is pick out descriptive content words—especially nouns and adjectives that convey imagery or substance.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     chức
    -0.07
    Den
    -0.06
     går
    -0.06
     pinpoint
    -0.06
     Density
    -0.06
    (query
    -0.06
     UEFA
    -0.06
    rpm
    -0.06
    Year
    -0.06
    296
    -0.06
    POSITIVE LOGITS
    Ђ
    0.08
    ickerView
    0.08
    .Try
    0.08
    .friends
    0.07
    _browser
    0.06
    ै,
    0.06
     exhibited
    0.06
     ovar
    0.06
    itters
    0.06
    .reload
    0.06
    Act Density 0.043%

    No Known Activations