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

    Neuronpedia

    INDEX
    Explanations

    !

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.68
    IVEREF
    -0.66
    ')")
    -0.64
    ReusableCell
    -0.62
    DebuggerNonUser
    -0.62
     betweenstory
    -0.60
    rrggbb
    -0.60
     Italijani
    -0.60
    ChildScrollView
    -0.58
     للمعارف
    -0.58
    POSITIVE LOGITS
     nhiêu
    0.56
     được
    0.56
     réponse
    0.51
     Gautier
    0.50
    /(
    0.49
    сний
    0.48
     réponses
    0.48
     Jacoby
    0.47
    denominator
    0.46
     Wett
    0.45
    Act Density 0.003%

    No Known Activations