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

    Neuronpedia

    INDEX
    Explanations

    trial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    racak
    -0.07
     tongues
    -0.06
    .HtmlControls
    -0.06
    edics
    -0.06
     Selector
    -0.06
    ぶ
    -0.06
    (hdc
    -0.06
    яв
    -0.06
     项
    -0.06
    Extent
    -0.06
    POSITIVE LOGITS
    //↵↵↵
    0.07
    (argument
    0.07
     dismissing
    0.06
    ове
    0.06
    0.06
    ================================================================================
    0.06
     bbw
    0.06
    ordinate
    0.06
     Kazakhstan
    0.06
     μικ
    0.06
    Act Density 0.004%

    No Known Activations