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

    Neuronpedia

    INDEX
    Explanations

    crying/sadness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =$(
    -0.08
        ↵    ↵
    -0.07
    expl
    -0.07
    );↵↵↵↵↵
    -0.07
     folly
    -0.07
    ED
    -0.06
    /exp
    -0.06
    ")}
    -0.06
    (exc
    -0.06
    ()],
    -0.06
    POSITIVE LOGITS
    awn
    0.07
    孓
    0.07
    찧
    0.07
    뱀
    0.07
    甏
    0.07
    丧失
    0.07
    キャッシ
    0.07
    ᴴ
    0.07
    얽
    0.07
    akk
    0.07
    Act Density 0.030%

    No Known Activations