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

    Neuronpedia

    INDEX
    Explanations

    designer, collection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Noise
    -0.07
     obedience
    -0.07
     روند
    -0.07
     strcat
    -0.07
    EntityManager
    -0.07
    ukes
    -0.06
     반환
    -0.06
    ほ
    -0.06
     sanctuary
    -0.06
    .NONE
    -0.06
    POSITIVE LOGITS
    =new
    0.07
     capacit
    0.07
     determining
    0.07
     muslim
    0.07
     buckle
    0.06
     Mens
    0.06
     testimonials
    0.06
     Drawable
    0.06
    *z
    0.06
     SPD
    0.06
    Act Density 0.028%

    No Known Activations