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

    Neuronpedia

    INDEX
    Explanations

    Compass directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ジオ
    -0.07
    slots
    -0.06
     recalls
    -0.06
     متحده
    -0.06
    ौट
    -0.06
    ::::::::::
    -0.06
     POV
    -0.06
     ORIGINAL
    -0.06
    peek
    -0.06
    ap
    -0.06
    POSITIVE LOGITS
     itemList
    0.07
     orderly
    0.07
     intimate
    0.07
    nek
    0.07
     billed
    0.06
     Sokol
    0.06
    
    0.06
     Mal
    0.06
    -stack
    0.06
     فال
    0.06
    Act Density 0.010%

    No Known Activations