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

    Neuronpedia

    INDEX
    Explanations

    sequential steps and decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    0.57
    дини
    0.48
    a
    0.48
    South
    0.46
     permesso
    0.46
    ۲
    0.45
    วิน
    0.45
    angement
    0.45
    rivate
    0.44
    posizione
    0.44
    POSITIVE LOGITS
     prefque
    0.57
    ，”
    0.47
    笛
    0.46
    ”;
    0.45
    }:=
    0.44
     đặc
    0.43
    转化
    0.43
    कार्ट
    0.43
    AddField
    0.42
     非
    0.42
    Act Density 0.000%

    No Known Activations