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

    Neuronpedia

    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Prepare
    -0.07
     tầm
    -0.07
    尊
    -0.07
     eventName
    -0.07
     Gibson
    -0.06
    ;
↵
↵
↵
    -0.06
     komb
    -0.06
     letterSpacing
    -0.06
    /*****************************************************************************↵
    -0.06
     +↵
    -0.06
    POSITIVE LOGITS
    elu
    0.07
     transporting
    0.07
    昇
    0.06
    characters
    0.06
     realistically
    0.06
     allocation
    0.06
    orphic
    0.06
     isol
    0.06
    áfico
    0.06
     faction
    0.06
    Act Density 0.029%

    No Known Activations