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
     หาก
    -0.07
    .Vert
    -0.07
    Reject
    -0.07
    nowrap
    -0.06
     بوابة
    -0.06
     toItem
    -0.06
     STATUS
    -0.06
     telegram
    -0.06
     khô
    -0.06
    -A
    -0.06
    POSITIVE LOGITS
    ा।↵↵
    0.07
    팅
    0.06
     kred
    0.06
     rigged
    0.06
    igration
    0.06
    Monthly
    0.06
     dispos
    0.06
    nosis
    0.06
    (py
    0.06
    _mount
    0.06
    Act Density 0.079%

    No Known Activations