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

    Neuronpedia

    INDEX
    Explanations

    another

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Be
    -0.08
    <select
    -0.07
     تلویزی
    -0.07
     GTK
    -0.07
    	for
    -0.07
    New
    -0.07
    enské
    -0.07
     cada
    -0.07
     его
    -0.07
    acia
    -0.07
    POSITIVE LOGITS
    know
    0.06
     interruption
    0.06
    .matrix
    0.06
    egt
    0.06
     привед
    0.06
    .isAdmin
    0.06
     cuc
    0.06
    ินด
    0.05
    landers
    0.05
    oplay
    0.05
    Act Density 0.026%

    No Known Activations