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

    Neuronpedia

    INDEX
    Explanations

    consider renting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.61
    ’
    0.58
    '
    0.57
    0.54
    l
    0.52
    .
    0.49
    ."
    0.47
    /
    0.46
     Basics
    0.46
     and
    0.45
    POSITIVE LOGITS
     malice
    0.40
    𝗢
    0.40
     ಪ್ರತಿ
    0.39
     विद्युत
    0.38
     陳
    0.37
     thèse
    0.37
    繭
    0.37
     אל
    0.36
     nuovamente
    0.36
     dirigés
    0.36
    Act Density 0.143%

    No Known Activations