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

    Neuronpedia

    INDEX
    Explanations

    identifying as "I" or "I am"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diel
    0.31
    цене
    0.30
    ましょう
    0.29
     specifications
    0.29
    ριο
    0.29
     thisobject
    0.29
    вара
    0.29
     amplitudes
    0.28
    פה
    0.28
    Delimiter
    0.28
    POSITIVE LOGITS
     मैं
    0.50
    मैं
    0.49
    我很
    0.49
    我现在
    0.49
     люблю
    0.48
     నేను
    0.46
     আমি
    0.46
    我是
    0.46
    私は
    0.45
    我会
    0.45
    Act Density 0.269%

    No Known Activations