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

    Neuronpedia

    INDEX
    Explanations

    film and media categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	So
    -0.07
     ideological
    -0.06
    �
    -0.06
     talking
    -0.06
    _mtx
    -0.06
     end
    -0.06
     ideology
    -0.06
    него
    -0.06
     Writer
    -0.06
    	ms
    -0.06
    POSITIVE LOGITS
    并
    0.07
     حالی
    0.07
    _UNSUPPORTED
    0.07
     教
    0.07
     glyphicon
    0.06
    ING
    0.06
    451
    0.06
    _TRANSACTION
    0.06
     unsettling
    0.06
    .NaN
    0.06
    Act Density 0.003%

    No Known Activations