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

    Neuronpedia

    INDEX
    Explanations

    freedom/degrees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    odule
    -0.07
     mesma
    -0.07
    Mat
    -0.07
    _topics
    -0.07
     Album
    -0.07
     Crisis
    -0.06
     neuroscience
    -0.06
     dz
    -0.06
     voz
    -0.06
     pict
    -0.06
    POSITIVE LOGITS
    ){↵↵
    0.06
    UGHT
    0.06
    皆
    0.05
    �
    0.05
    गढ
    0.05
    (filters
    0.05
    _strerror
    0.05
    estr
    0.05
     стрем
    0.05
     adjusted
    0.05
    Act Density 0.016%

    No Known Activations