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

    Neuronpedia

    INDEX
    Explanations

    light

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    莉
    -0.07
     правда
    -0.06
    useppe
    -0.06
    /console
    -0.06
    stddef
    -0.06
    Mappings
    -0.06
     verz
    -0.06
    سل
    -0.06
    }}">{{$
    -0.06
     cerc
    -0.06
    POSITIVE LOGITS
     loss
    0.06
     nfl
    0.06
    ^K
    0.06
     MOR
    0.06
    bj
    0.06
    τικο
    0.06
     Titles
    0.06
    运动
    0.06
    uards
    0.06
    níka
    0.06
    Act Density 0.008%

    No Known Activations