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

    Neuronpedia

    INDEX
    Explanations

    serious or indicator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     उद्योग
    0.48
     criticisms
    0.47
     criticism
    0.46
     severity
    0.46
     Criticism
    0.44
    検出
    0.44
     निया
    0.43
     fonctionnement
    0.43
     dramas
    0.42
     विवाद
    0.42
    POSITIVE LOGITS
     slob
    0.48
    orski
    0.46
    войства
    0.45
    ற்ச
    0.45
    Devil
    0.44
    𝚕
    0.44
    льм
    0.44
    л
    0.44
    да
    0.43
    Fire
    0.43
    Act Density 0.006%

    No Known Activations