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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    flo
    -0.07
    骨
    -0.06
     slows
    -0.06
     НА
    -0.06
    modifiers
    -0.06
     progressed
    -0.06
    returned
    -0.06
     fern
    -0.06
    constitution
    -0.06
     capac
    -0.06
    POSITIVE LOGITS
     Laser
    0.07
     breaches
    0.07
    //{{
    0.06
     Listen
    0.06
     celebrate
    0.06
     EIF
    0.06
    (Photo
    0.06
     lob
    0.06
     خود
    0.06
    DF
    0.06
    Act Density 0.001%

    No Known Activations