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

    Neuronpedia

    INDEX
    Explanations

    code explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sepan
    0.73
     die
    0.69
    die
    0.68
     abc
    0.66
    \|
    0.65
    Monica
    0.64
     Bev
    0.64
     Die
    0.63
     sec
    0.63
     determined
    0.63
    POSITIVE LOGITS
    frameN
    0.85
    merksamkeit
    0.76
    话题
    0.73
     ஓர
    0.72
    URACY
    0.72
    ልቅ
    0.71
    ᄊ
    0.70
    řad
    0.70
     plowed
    0.69
    าที
    0.69
    Act Density 0.008%

    No Known Activations