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

    Neuronpedia

    INDEX
    Explanations

    by, from, to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     точки
    -0.08
    宽
    -0.07
    下一个
    -0.07
    arrant
    -0.06
     Beyond
    -0.06
    ᨵ
    -0.06
    矣
    -0.06
     eben
    -0.06
    	se
    -0.06
    往
    -0.06
    POSITIVE LOGITS
    _team
    0.07
    贴心
    0.07
    MERCHANTABILITY
    0.07
     Trait
    0.07
    -selling
    0.07
    🐯
    0.07
    ארג
    0.06
    (dest
    0.06
    _COND
    0.06
    LOB
    0.06
    Act Density 0.024%

    No Known Activations