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

    Neuronpedia

    INDEX
    Explanations

    code and software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    those
    0.39
    Those
    0.36
     उनमें
    0.36
     quelli
    0.35
     Those
    0.33
     ceux
    0.33
     those
    0.33
    eness
    0.32
    พวกเขา
    0.32
    pyrim
    0.32
    POSITIVE LOGITS
    Pieces
    0.44
     pieces
    0.40
     которое
    0.40
    जात
    0.38
    stuk
    0.36
     Pieces
    0.35
     केली
    0.35
    stücke
    0.35
     itself
    0.34
    片段
    0.34
    Act Density 0.176%

    No Known Activations