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

    Neuronpedia

    INDEX
    Explanations

    conda create or activate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    0.73
    r
    0.73
    ों
    0.68
    1
    0.67
    l
    0.65
    ъ
    0.65
    d
    0.64
     preci
    0.63
    oacute
    0.63
     NSLog
    0.63
    POSITIVE LOGITS
     बदल
    0.56
     वाट
    0.51
     بدل
    0.49
    (“
    0.49
     چند
    0.48
     만들
    0.47
     편
    0.47
     조금
    0.47
     過
    0.47
     chút
    0.47
    Act Density 0.006%

    No Known Activations