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

    Neuronpedia

    INDEX
    Explanations

    konnichiwa, shalom, bonjour

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.52
    1.16
     I
    1.11
     (
    1.08
    an
    1.04
    ן
    1.04
    gie
    1.01
    k
    0.99
     A
    0.98
    are
    0.95
    POSITIVE LOGITS
    ગ
    0.92
    도
    0.91
     bxa
    0.90
     prennent
    0.90
    ತ
    0.90
    ᱗
    0.90
    ма
    0.90
     seleccione
    0.88
    ﺐ
    0.88
     vídeo
    0.87
    Act Density 0.000%

    No Known Activations