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

    Neuronpedia

    INDEX
    Explanations

    casting speculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Confirmation
    -0.07
     Bankası
    -0.07
     carrera
    -0.06
     Couple
    -0.06
     Heather
    -0.06
     Oversight
    -0.06
     Santa
    -0.06
    	async
    -0.06
     الوط
    -0.06
     stripper
    -0.06
    POSITIVE LOGITS
     *[
    0.06
    rift
    0.06
    889
    0.06
    333
    0.06
    �
    0.06
    iceps
    0.06
    ActionBar
    0.06
    .pag
    0.06
     unins
    0.05
     أد
    0.05
    Act Density 0.013%

    No Known Activations