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

    Neuronpedia

    INDEX
    Explanations

    terms and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Eig
    -0.92
    banken
    -0.88
     Đức
    -0.82
     flotte
    -0.81
    ynchro
    -0.81
     stoff
    -0.80
     kennen
    -0.79
    包子
    -0.79
    atla
    -0.79
    が良い
    -0.79
    POSITIVE LOGITS
     Ministério
    0.82
    操
    0.80
    WebApplication
    0.78
    ricate
    0.77
    少女
    0.76
    휴
    0.76
    ghế
    0.76
     jardim
    0.75
    acad
    0.75
    了一口气
    0.75
    Act Density 0.260%

    No Known Activations