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

    Neuronpedia

    INDEX
    Explanations

    systemctl commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nape
    0.79
    igl
    0.78
     morales
    0.77
     realidade
    0.73
     estrada
    0.73
    neau
    0.72
    োগ্রাফ
    0.72
    鶴
    0.70
    ROE
    0.70
     القسمه
    0.69
    POSITIVE LOGITS
    ாய
    0.76
    αιν
    0.61
     plist
    0.59
    fileID
    0.58
    Charging
    0.58
    恂
    0.58
    zechoslovakia
    0.57
    ω
    0.57
    Scissors
    0.57
     Idi
    0.56
    Act Density 0.037%

    No Known Activations