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

    Neuronpedia

    INDEX
    Explanations

    types and merge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     カード
    0.43
     panel
    0.42
     impurities
    0.42
     destroy
    0.41
     pacing
    0.40
     parser
    0.40
    gnię
    0.39
     chimeric
    0.39
    owane
    0.39
     personalized
    0.39
    POSITIVE LOGITS
    安
    0.42
    去看
    0.40
    علام
    0.40
     školy
    0.37
    ösen
    0.37
    当
    0.37
     marcar
    0.37
     Spartans
    0.37
    足を
    0.37
     unmarked
    0.36
    Act Density 0.000%

    No Known Activations