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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     backsplash
    -0.09
     verhindert
    -0.08
     स्थल
    -0.07
    阻
    -0.07
    ostream
    -0.07
     विरोध
    -0.07
    GST
    -0.07
    uct
    -0.07
     vantage
    -0.07
    สถาน
    -0.07
    POSITIVE LOGITS
    ינען
    0.08
    нае
    0.08
    াউ
    0.08
    hnte
    0.07
     tarea
    0.07
     Фин
    0.07
    নে
    0.07
     Chico
    0.07
     netij
    0.07
    ുന്നത
    0.07
    Act Density 0.000%

    No Known Activations