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

    Neuronpedia

    INDEX
    Explanations

    grading focus on requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     насеко
    0.51
    ğlu
    0.48
    뀜
    0.48
     घड
    0.48
     ప్రపంచ
    0.46
    hams
    0.46
     اسمه
    0.46
     కుటు
    0.46
     언급
    0.46
     आउटफिट
    0.45
    POSITIVE LOGITS
     in
    0.54
     cannot
    0.44
    ,
    0.44
     uniquement
    0.42
     dispositivo
    0.42
    //
    0.42
     votre
    0.42
    I
    0.42
     as
    0.41
    p
    0.41
    Act Density 0.002%

    No Known Activations