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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     десят
    -0.07
    ضافة
    -0.07
    BO
    -0.06
    Lat
    -0.06
     Ου
    -0.06
    .Bot
    -0.06
     wasm
    -0.06
     示例
    -0.06
     Display
    -0.06
    ./
    -0.06
    POSITIVE LOGITS
     Regarding
    0.07
     hates
    0.07
    342
    0.06
     Accom
    0.06
     cooking
    0.06
    .after
    0.06
     tariffs
    0.06
     Thai
    0.06
     requesting
    0.06
    ุข
    0.06
    Act Density 0.011%

    No Known Activations