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

    Neuronpedia

    INDEX
    Explanations

    parse

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Superior
    -0.07
    intersection
    -0.07
     스포츠
    -0.06
     QPushButton
    -0.06
     VT
    -0.06
     monitored
    -0.06
     EventHandler
    -0.06
     upgrade
    -0.06
    .time
    -0.06
     Dwight
    -0.06
    POSITIVE LOGITS
    Much
    0.07
    part
    0.07
    誌
    0.07
    Parse
    0.06
    поч
    0.06
     omas
    0.06
    ovací
    0.06
    목
    0.06
    0.06
     parte
    0.06
    Act Density 0.014%

    No Known Activations