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

    Neuronpedia

    INDEX
    Explanations

    wishes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onitor
    -0.07
     getService
    -0.07
     адміністратив
    -0.07
     Highly
    -0.06
     Dane
    -0.06
    adians
    -0.06
     refuses
    -0.06
     quaternion
    -0.06
    ポイント
    -0.06
    .setColumns
    -0.06
    POSITIVE LOGITS
     vais
    0.06
    ("[
    0.06
    George
    0.06
    insky
    0.06
     commander
    0.06
    melon
    0.06
    *******************************************************************************/↵
    0.06
    >↵↵
    0.06
     weddings
    0.06
    []↵
    0.06
    Act Density 0.014%

    No Known Activations