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

    Neuronpedia

    INDEX
    Explanations

    PyInstaller or religious terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.65
    wen
    0.63
     amigo
    0.61
    ti
    0.61
     நண்ப
    0.61
    ietic
    0.59
    rę
    0.58
    ibre
    0.58
     話
    0.58
     நீண்ட
    0.58
    POSITIVE LOGITS
    ق
    0.67
    ENCY
    0.55
    ع
    0.54
    燃
    0.53
    Buen
    0.52
    禳
    0.52
    ES
    0.51
    ERICK
    0.51
     Derr
    0.51
    UNIVERSITY
    0.50
    Act Density 0.000%

    No Known Activations