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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Enc
    -0.07
    forEach
    -0.07
    Dep
    -0.06
    Pager
    -0.06
    wives
    -0.06
    Franc
    -0.06
    "P
    -0.06
    Chess
    -0.06
    …)
    -0.06
    Arr
    -0.06
    POSITIVE LOGITS
    /py
    0.07
     tweaked
    0.06
     persecuted
    0.06
    .Keyboard
    0.06
    ähl
    0.06
     ITEMS
    0.06
     neby
    0.06
    َو
    0.06
     مما
    0.06
     tallest
    0.06
    Act Density 0.024%

    No Known Activations