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

    Neuronpedia

    INDEX
    Explanations

    technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -INF
    -0.07
    chn
    -0.06
     gone
    -0.06
     Fra
    -0.06
    Component
    -0.06
     Стар
    -0.06
     Wellness
    -0.06
    终于
    -0.06
    导致
    -0.06
    ugas
    -0.06
    POSITIVE LOGITS
    ];↵↵↵
    0.07
    Listening
    0.07
    %@",
    0.07
     Bicycle
    0.07
     Greens
    0.07
    epy
    0.06
    녕
    0.06
    ricanes
    0.06
    209
    0.06
    consin
    0.06
    Act Density 0.000%

    No Known Activations