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

    Neuronpedia

    INDEX
    Explanations

    Winning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thetic
    -0.07
     tienes
    -0.06
    Parking
    -0.06
     linger
    -0.06
     ])↵↵
    -0.06
    STATE
    -0.06
     Bring
    -0.06
    ).↵↵↵↵
    -0.06
    .')↵↵
    -0.06
     Ver
    -0.06
    POSITIVE LOGITS
     Ren
    0.07
     Основ
    0.07
     zákon
    0.07
    ABEL
    0.06
     Společ
    0.06
    .compare
    0.06
    ové
    0.06
     coordin
    0.06
     अस
    0.06
     NSF
    0.06
    Act Density 0.042%

    No Known Activations