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

    Neuronpedia

    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     엘
    -0.07
    .application
    -0.07
    ビ
    -0.06
    _Tr
    -0.06
    โอ
    -0.06
     भ
    -0.06
    フ�
    -0.06
     समस
    -0.06
     Belediyesi
    -0.06
    주시
    -0.06
    POSITIVE LOGITS
    ”。↵↵
    0.06
     bowls
    0.06
    _SAFE
    0.06
     substances
    0.06
     Daughter
    0.05
    educ
    0.05
     Opport
    0.05
    SEND
    0.05
     هنگام
    0.05
     customization
    0.05
    Act Density 0.008%

    No Known Activations