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

    Neuronpedia

    INDEX
    Explanations

    linking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     =(
    -0.07
     haya
    -0.06
     proč
    -0.06
     shift
    -0.06
    (script
    -0.06
     Insert
    -0.06
     uttered
    -0.06
     Але
    -0.06
     Werk
    -0.06
     stunt
    -0.06
    POSITIVE LOGITS
     valor
    0.07
    ARM
    0.07
    _HC
    0.06
    LOGIN
    0.06
    /apis
    0.06
    werp
    0.06
    葉
    0.06
     radi
    0.06
    IVE
    0.06
     طبیعی
    0.06
    Act Density 0.000%

    No Known Activations