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

    Neuronpedia

    INDEX
    Explanations

    vounger brothers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arms
    0.45
    hv
    0.43
     Wav
    0.43
    sempel
    0.41
    ෲ
    0.40
    嵌入
    0.39
    mlabeledtr
    0.39
     Hv
    0.38
    ніше
    0.38
    wv
    0.38
    POSITIVE LOGITS
     conceitos
    0.55
     utilisez
    0.54
     இல்லாத
    0.54
     gói
    0.53
     החד
    0.51
     infusions
    0.50
     ವೇ
    0.50
     modernos
    0.49
     têm
    0.49
     utilise
    0.49
    Act Density 0.000%

    No Known Activations