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

    Neuronpedia

    INDEX
    Explanations

    Diagram labels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abrupt
    -0.06
     abrir
    -0.06
    .exceptions
    -0.06
     visitor
    -0.06
    .change
    -0.06
     assisted
    -0.06
    ць
    -0.06
    adv
    -0.06
    vertising
    -0.06
    	person
    -0.06
    POSITIVE LOGITS
     Georgetown
    0.07
    inations
    0.07
     Greenville
    0.07
    _cnt
    0.07
     bied
    0.07
     conjunction
    0.06
     Dynam
    0.06
     Leg
    0.06
    aal
    0.06
    ModelIndex
    0.06
    Act Density 0.002%

    No Known Activations