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

    Neuronpedia

    INDEX
    Explanations

    numerical comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (host
    -0.06
    Vars
    -0.06
     Bottom
    -0.06
     thân
    -0.06
    znám
    -0.06
    ğa
    -0.06
     MAV
    -0.06
     Converts
    -0.06
    _vc
    -0.06
    .sheet
    -0.06
    POSITIVE LOGITS
     chiếm
    0.07
    扱
    0.07
    >();
↵
    0.06
     ніж
    0.06
    ">'+
    0.06
     jclass
    0.06
     Ngoài
    0.06
    jspx
    0.06
    (rules
    0.06
    };
    0.06
    Act Density 0.014%

    No Known Activations