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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Anime
    -0.08
    宽阔
    -0.07
    万名
    -0.07
     attracts
    -0.07
    רוך
    -0.07
     Philadelphia
    -0.07
     лечения
    -0.07
     Sized
    -0.07
     Ukraine
    -0.07
     manner
    -0.06
    POSITIVE LOGITS
    .double
    0.07
    _constants
    0.06
    احتم
    0.06
    ﲝ
    0.06
    谇
    0.06
    ToolStripMenuItem
    0.06
    הפך
    0.06
    .har
    0.06
    헤
    0.06
    无效
    0.06
    Act Density 0.003%

    No Known Activations