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

    Neuronpedia

    INDEX
    Explanations

    also, in addition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waarmee
    0.39
     olmuş
    0.35
     című
    0.34
    اؤن
    0.33
     multimillion
    0.32
     telah
    0.31
    ايا
    0.31
     clockRadius
    0.31
     уту
    0.31
     شاہ
    0.31
    POSITIVE LOGITS
     also
    0.88
     также
    0.84
     myös
    0.73
     גם
    0.73
    also
    0.68
     також
    0.68
     همچنین
    0.66
     aussi
    0.66
    也可以
    0.65
     Также
    0.65
    Act Density 1.028%

    No Known Activations