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

    Neuronpedia

    INDEX
    Explanations

    possibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Garr
    -0.08
    ល
    -0.07
    쎈
    -0.07
     kits
    -0.07
    Daemon
    -0.07
    癸
    -0.06
    Had
    -0.06
    搞好
    -0.06
     Emmy
    -0.06
     compass
    -0.06
    POSITIVE LOGITS
    자
    0.07
     crossorigin
    0.07
    렵
    0.07
    WithTitle
    0.07
    葡萄酒
    0.07
     cosmos
    0.07
    쟛
    0.06
     iş
    0.06
    眼
    0.06
    ược
    0.06
    Act Density 0.128%

    No Known Activations