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

    Neuronpedia

    INDEX
    Explanations

    machine learning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prosper
    -0.08
     девуш
    -0.07
     robbery
    -0.07
    托福
    -0.07
    欢呼
    -0.07
     blackmail
    -0.07
     ejac
    -0.07
    (mysqli
    -0.07
     cour
    -0.06
     Christmas
    -0.06
    POSITIVE LOGITS
     borderSide
    0.07
    תיקון
    0.07
    聘请
    0.07
    创造了
    0.07
    出自
    0.06
    Bin
    0.06
    入住
    0.06
    .der
    0.06
    Od
    0.06
    琴
    0.06
    Act Density 0.019%

    No Known Activations