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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    מפק
    -0.07
     물론
    -0.07
     ראשון
    -0.06
     impunity
    -0.06
    .pages
    -0.06
    simp
    -0.06
    .View
    -0.06
    טופ
    -0.06
    Ő
    -0.06
    路况
    -0.06
    POSITIVE LOGITS
     nitrogen
    0.08
    所得
    0.07
     transient
    0.07
    _nbr
    0.07
    炭
    0.07
    -ring
    0.07
    调剂
    0.07
    (target
    0.07
    .WriteLine
    0.07
    陶瓷
    0.06
    Act Density 0.012%

    No Known Activations