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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VR
    -0.07
     regression
    -0.07
    	ERR
    -0.06
    -old
    -0.06
    vincial
    -0.06
    Serialization
    -0.06
     manslaughter
    -0.06
     abandoned
    -0.06
    -stage
    -0.06
     US
    -0.06
    POSITIVE LOGITS
    问题
    0.06
    _PROC
    0.06
     elim
    0.06
    เทพ
    0.06
     değişik
    0.06
    .Strings
    0.06
     جديد
    0.06
    ]";↵
    0.06
     UIEdgeInsets
    0.06
    .ev
    0.06
    Act Density 0.034%

    No Known Activations