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

    Neuronpedia

    INDEX
    Explanations

    generating scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.44
     Bowls
    0.43
    Picture
    0.43
    全
    0.42
    4
    0.41
    マ
    0.40
    ゴ
    0.40
    core
    0.40
    0.40
    9
    0.40
    POSITIVE LOGITS
     problemi
    0.63
     рэгістра
    0.55
     permasalahan
    0.54
     OBSERV
    0.54
     sintomas
    0.54
     problemy
    0.52
     pengetahuan
    0.52
     mempelajari
    0.52
     masalah
    0.51
     جوہری
    0.51
    Act Density 0.000%

    No Known Activations