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

    Neuronpedia

    INDEX
    Explanations

    resistance words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dairy
    0.46
    tem
    0.46
    汥
    0.46
    isRunning
    0.43
    sted
    0.42
     Of
    0.41
    etat
    0.41
    し
    0.41
    surprisingly
    0.40
    STANDING
    0.40
    POSITIVE LOGITS
     memakai
    0.49
     basados
    0.46
    ियन
    0.45
     pictured
    0.45
     geometria
    0.45
     portada
    0.45
    ညာ
    0.45
     vantagens
    0.45
    នៅលើ
    0.44
     maneiras
    0.44
    Act Density 0.002%

    No Known Activations