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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >";
    -0.82
    ymus
    -0.79
     hẳn
    -0.75
     Baptists
    -0.72
    plets
    -0.72
    둬
    -0.71
     Poppy
    -0.71
    sql
    -0.69
     承
    -0.69
    ラル
    -0.69
    POSITIVE LOGITS
     век
    0.71
     ה
    0.70
    Horrible
    0.69
    ips
    0.68
     buck
    0.67
    billon
    0.65
     Thesaurus
    0.64
    Funktionen
    0.63
    %%%%%%%%
    0.63
     korban
    0.63
    Act Density 0.023%

    No Known Activations