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

    Neuronpedia

    INDEX
    Explanations

    options and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     extremities
    0.45
    锜
    0.44
     intercepts
    0.40
    separatedBy
    0.38
     ክፍል
    0.37
     مستوى
    0.36
    ARAJ
    0.36
    iosa
    0.36
     ниво
    0.36
    塙
    0.36
    POSITIVE LOGITS
    ทย
    0.37
    UIApplication
    0.37
    brooke
    0.37
     penuh
    0.36
     proff
    0.36
     tash
    0.35
     dire
    0.33
    Reuters
    0.33
     calming
    0.33
     nes
    0.33
    Act Density 0.002%

    No Known Activations