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

    Neuronpedia

    INDEX
    Explanations

    South Dakota

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iddle
    0.40
    ['-
    0.40
    ക്കാണ്
    0.39
    ພັນ
    0.39
    騁
    0.38
     wash
    0.38
    antation
    0.38
    ulación
    0.37
     KP
    0.37
     naw
    0.37
    POSITIVE LOGITS
     Pip
    0.62
    Pip
    0.53
     Brookings
    0.52
     pip
    0.50
    Adrian
    0.46
     Volga
    0.46
    Jasper
    0.45
     Hendricks
    0.44
    pip
    0.44
    Brook
    0.44
    Act Density 0.001%

    No Known Activations