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

    Neuronpedia

    INDEX
    Explanations

    news representation

    np_max-act · gemini-2.0-flash

    This neuron responds to words indicating attribution of statements or sourcing (e.g. “said,” “spokesman,” “manager,” “source,” “representatives”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .hide
    -0.07
     invis
    -0.07
    	store
    -0.06
    share
    -0.06
     Phil
    -0.06
    ülebilir
    -0.06
     bibli
    -0.06
    /app
    -0.06
    	Write
    -0.06
    .update
    -0.06
    POSITIVE LOGITS
     boxShadow
    0.07
    _YELLOW
    0.07
    atır
    0.07
     Applying
    0.06
     wf
    0.06
    spiel
    0.06
     drm
    0.06
     měsí
    0.06
    џџџџџџџџ
    0.06
     tours
    0.06
    Act Density 0.037%

    No Known Activations