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

    Neuronpedia

    INDEX
    Explanations

    While

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     χωρίς
    0.52
     mantenere
    0.51
     COE
    0.49
    л
    0.48
     stain
    0.46
     of
    0.46
     minors
    0.46
    ש
    0.46
     marinas
    0.46
     domicile
    0.46
    POSITIVE LOGITS
    bildungs
    0.57
    埂
    0.56
    formerly
    0.56
     arba
    0.55
     तब्
    0.54
    gelopen
    0.54
    eber
    0.53
    ഷ്ണ
    0.52
    D
    0.52
    াইড
    0.50
    Act Density 0.033%

    No Known Activations