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

    Neuronpedia

    INDEX
    Explanations

    Nonsense words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rocky
    -0.07
     Buddy
    -0.07
     Faculty
    -0.07
     Frame
    -0.06
     nghi
    -0.06
     advocates
    -0.06
    Bel
    -0.06
    Struct
    -0.06
    uggy
    -0.06
     Healthy
    -0.06
    POSITIVE LOGITS
     čast
    0.07
    оком
    0.06
     улуч
    0.06
    �
    0.06
    stellar
    0.06
    _Click
    0.06
    dig
    0.06
     iv
    0.06
    DON
    0.06
    znám
    0.06
    Act Density 0.008%

    No Known Activations