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

    Neuronpedia

    INDEX
    Explanations

    connecting list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ă
    0.39
    с
    0.35
    أ
    0.34
    ر
    0.33
     nào
    0.33
    А
    0.32
    三
    0.32
            
    0.32
     européen
    0.30
    ABCD
    0.30
    POSITIVE LOGITS
     zároveň
    0.54
     sekaligus
    0.40
    အတူ
    0.40
     साथ
    0.39
     secondly
    0.39
    גם
    0.38
     myös
    0.37
     आल्सो
    0.36
    也很
    0.36
     lastly
    0.36
    Act Density 0.082%

    No Known Activations