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

    Neuronpedia

    INDEX
    Explanations

    rainy day distractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    multiple
    0.43
     subject
    0.42
    fil
    0.40
    subject
    0.39
    word
    0.39
    surface
    0.39
    open
    0.38
     भूषण
    0.38
    human
    0.37
    assisted
    0.37
    POSITIVE LOGITS
     sostitu
    0.46
     richting
    0.42
     εγκα
    0.42
     영화
    0.42
    檩
    0.42
     artyku
    0.41
     питание
    0.40
     쭉
    0.40
    擠
    0.40
     remplacement
    0.40
    Act Density 0.000%

    No Known Activations