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

    Neuronpedia

    INDEX
    Explanations

    drawing lines slowly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /*
    0.47
     (&
    0.46
    ,
    0.45
    s
    0.43
    8
    0.42
    sst
    0.41
    3
    0.41
    9
    0.41
    bew
    0.41
    6
    0.40
    POSITIVE LOGITS
     በኋላ
    0.47
    Tangent
    0.47
    嘤
    0.45
    慵
    0.45
     উপভোগ
    0.44
     ሂደት
    0.43
     ဖ
    0.43
    мимо
    0.43
    คองโก
    0.43
    Aluno
    0.43
    Act Density 0.005%

    No Known Activations