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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emerge
    -0.06
    .work
    -0.06
    .ham
    -0.06
    604
    -0.06
     orderly
    -0.06
     Reputation
    -0.06
     indexing
    -0.06
    usta
    -0.05
     departed
    -0.05
    ��
    -0.05
    POSITIVE LOGITS
    exp
    0.07
    _LSB
    0.07
     serv
    0.07
    (constants
    0.06
    .ISupportInitialize
    0.06
    Rua
    0.06
    (interp
    0.06
     mm
    0.06
     axis
    0.06
    onacci
    0.06
    Act Density 0.000%

    No Known Activations