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

    Neuronpedia

    INDEX
    Explanations

    code and text snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </sup>
    -1.48
    Pyrene
    -1.32
    ghế
    -1.32
    Neder
    -1.31
    ();
    -1.31
    Sumber
    -1.30
    Fonto
    -1.30
     bianche
    -1.29
    掮
    -1.28
    甦
    -1.27
    POSITIVE LOGITS
    the
    1.64
     bestehende
    1.59
    瞟
    1.45
    both
    1.42
     Both
    1.39
     sogen
    1.36
    噤
    1.35
    鸲
    1.35
    撂
    1.34
     here
    1.33
    Act Density 0.151%

    No Known Activations