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

    Neuronpedia

    INDEX
    Explanations

    subtraction and remaining values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ornamental
    -0.07
     conver
    -0.07
     इसके
    -0.07
    .flat
    -0.07
     convergence
    -0.07
    *
    -0.07
    伸
    -0.07
    itif
    -0.07
     traditional
    -0.07
    *@
    -0.07
    POSITIVE LOGITS
    .remaining
    0.13
    剩
    0.13
     restantes
    0.12
    _remaining
    0.12
    remaining
    0.11
     restante
    0.10
    Remaining
    0.10
     leftover
    0.10
     ശേഷ
    0.10
     remaining
    0.10
    Act Density 0.017%

    No Known Activations