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

    Neuronpedia

    INDEX
    Explanations

    words starting with pre

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    пред
    0.44
    етра
    0.40
    ریض
    0.39
     Founder
    0.39
     příjem
    0.38
    énées
    0.37
     rectángulo
    0.37
    ালার
    0.37
    前景
    0.37
    かい
    0.36
    POSITIVE LOGITS
    posterous
    0.68
    emptive
    0.64
    hension
    0.59
    Pre
    0.55
    umably
    0.54
    hensive
    0.53
    cursor
    0.52
    cluding
    0.52
    pre
    0.49
     Pre
    0.49
    Act Density 0.087%

    No Known Activations