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

    Neuronpedia

    INDEX
    Explanations

    }pass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kert
    0.50
     Präsident
    0.48
     striis
    0.48
     kalimat
    0.47
    ća
    0.47
     kij
    0.46
     Priyanka
    0.45
     unul
    0.45
     Ná
    0.45
    ёт
    0.44
    POSITIVE LOGITS
    er
    0.69
    h
    0.61
    ח
    0.55
    al
    0.52
    ties
    0.52
    ing
    0.51
    nate
    0.49
    tech
    0.48
    ك
    0.47
     کن
    0.46
    Act Density 0.030%

    No Known Activations