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

    Neuronpedia

    INDEX
    Explanations

    dynamic behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Unary
    0.45
    Thickness
    0.41
    Small
    0.40
     چھ
    0.40
     enhancers
    0.40
    ഗ്
    0.39
    Groups
    0.39
    ClassNotFound
    0.39
    Repeating
    0.39
     நல
    0.39
    POSITIVE LOGITS
    كلات
    0.48
     proceed
    0.46
     reimburse
    0.46
     Bracelet
    0.46
     २४
    0.45
     संग्रहण
    0.45
     Lind
    0.44
    金を
    0.44
     advertise
    0.43
    ილები
    0.43
    Act Density 0.006%

    No Known Activations