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

    Neuronpedia

    INDEX
    Explanations

    warfare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.45
     purpoſe
    -1.27
     Majefty
    -1.23
     Anſ
    -1.21
     fubject
    -1.20
     myſelf
    -1.20
     ſeveral
    -1.20
     itſelf
    -1.20
     houſe
    -1.16
     Houſe
    -1.16
    POSITIVE LOGITS
    '
    0.56
    s
    0.49
    ’
    0.48
     referrerpolicy
    0.46
    ↵↵
    0.45
    </em>
    0.44
    HasColumnType
    0.44
    מבר
    0.43
     (
    0.42
    ся
    0.41
    Act Density 0.115%

    No Known Activations