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
    )));↵↵
    -0.08
     e
    -0.08
    创新创业
    -0.07
     rencontrer
    -0.07
    组织领导
    -0.07
     adulte
    -0.07
    	border
    -0.07
     live
    -0.07
     Applied
    -0.07
     living
    -0.07
    POSITIVE LOGITS
     Tok
    0.07
    �
    0.07
    全球化
    0.07
    .EndsWith
    0.07
     kości
    0.07
     undercut
    0.07
    ⮞
    0.07
    っぽ
    0.07
    犒
    0.07
    撺
    0.06
    Act Density 0.006%

    No Known Activations