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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting image‐ or photo‐caption phrases, such as brief descriptive lines and photo credits.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Editor
    -0.07
     cardiac
    -0.06
    quan
    -0.06
     osobních
    -0.06
     bubble
    -0.06
    spam
    -0.06
    bor
    -0.06
     scan
    -0.06
     annihil
    -0.06
    oston
    -0.06
    POSITIVE LOGITS
    /messages
    0.07
    	LOG
    0.07
     заяви
    0.07
     *)↵↵
    0.06
     Penguins
    0.06
     الحي
    0.06
     والت
    0.06
    เส
    0.06
     �
    0.06
     rost
    0.06
    Act Density 0.020%

    No Known Activations