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

    Neuronpedia

    INDEX
    Explanations

    negation related to inability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Payload
    -0.07
     Powder
    -0.06
     Spit
    -0.06
     рей
    -0.06
     medication
    -0.06
     organization
    -0.06
     disabled
    -0.06
    _IMAGES
    -0.06
    _npc
    -0.05
    -review
    -0.05
    POSITIVE LOGITS
    承
    0.07
     проведення
    0.07
     六
    0.07
    unsigned
    0.07
     os
    0.06
    inject
    0.06
     začala
    0.06
    	background
    0.06
    _keywords
    0.06
     rá
    0.06
    Act Density 0.020%

    No Known Activations