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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    发表于
    -0.85
    
    -0.72
    WriteBarrier
    -0.72
    UserScript
    -0.69
     }{@
    -0.68
    原始内容存档于
    -0.66
    __":
    -0.63
     createState
    -0.63
    +:+
    -0.63
    Искәрмәләр
    -0.60
    POSITIVE LOGITS
    complexContent
    0.46
    jsonwebtoken
    0.42
     hObject
    0.40
    CancelButton
    0.37
    anță
    0.36
    empty
    0.35
    ENTIAL
    0.35
    Previews
    0.34
    Saf
    0.34
     passos
    0.34
    Act Density 0.001%

    No Known Activations