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

    Neuronpedia

    INDEX
    Explanations

    plot label rotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kw
    0.52
    rt
    0.52
    ен
    0.48
    ъ
    0.48
    le
    0.48
    rm
    0.47
    ish
    0.47
    iz
    0.46
    ig
    0.45
     I
    0.44
    POSITIVE LOGITS
     hér
    0.44
    👅
    0.43
    早在
    0.42
    🏨
    0.42
    ólico
    0.42
    🧴
    0.41
     européenne
    0.41
     کړئ
    0.41
     straightened
    0.41
     깔
    0.40
    Act Density 0.002%

    No Known Activations