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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ीर
    -0.07
    -called
    -0.06
    Safe
    -0.06
    olar
    -0.06
    pie
    -0.06
    sleep
    -0.06
    нош
    -0.06
    _hop
    -0.06
    írk
    -0.06
    dess
    -0.06
    POSITIVE LOGITS
     بند
    0.08
    'post
    0.08
     školy
    0.07
     countert
    0.07
     Croatia
    0.07
     ammunition
    0.06
     Lehr
    0.06
    /***************************************************************************↵
    0.06
     上海
    0.06
     ऑफ
    0.06
    Act Density 0.125%

    No Known Activations