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

    Neuronpedia

    INDEX
    Explanations

    cannot even attempt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vehement
    0.45
     mainstream
    0.45
     multiplicative
    0.44
    ជាមួយនឹង
    0.43
     ahora
    0.43
     totalitarian
    0.43
     बवाल
    0.43
     scary
    0.43
     倍
    0.43
     الآن
    0.42
    POSITIVE LOGITS
     προϊ
    0.45
     driftwood
    0.41
    વાસ
    0.40
     হইয়াছিল
    0.40
     त्यांची
    0.40
     encamp
    0.39
    ି
    0.39
     Johnston
    0.39
    Ĥ
    0.38
    車站
    0.38
    Act Density 0.002%

    No Known Activations