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

    Neuronpedia

    INDEX
    Explanations

    review discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     care
    0.45
     Arrival
    0.45
    care
    0.44
     fau
    0.44
     reklam
    0.43
     wash
    0.42
     tak
    0.42
     Corporate
    0.42
     vær
    0.42
     ideas
    0.41
    POSITIVE LOGITS
    者的
    0.54
    ers
    0.53
    धीन
    0.52
    annya
    0.51
    ę
    0.50
    अर्स
    0.48
    ст
    0.47
    тити
    0.47
    сте
    0.47
    рина
    0.46
    Act Density 0.006%

    No Known Activations