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

    Neuronpedia

    INDEX
    Explanations

    bract / brack / brach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ശു
    0.43
     preferencias
    0.42
     전달
    0.42
    owice
    0.41
    賂
    0.41
    jekte
    0.41
     patrols
    0.40
     కామె
    0.40
     comedies
    0.40
     exteriores
    0.40
    POSITIVE LOGITS
     tracker
    0.38
     بی‌
    0.37
     loo
    0.36
    Fail
    0.35
     FAIL
    0.35
    wirk
    0.34
    TRACK
    0.34
     Encoder
    0.33
     سەر
    0.33
    μπ
    0.33
    Act Density 0.001%

    No Known Activations