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

    Neuronpedia

    INDEX
    Explanations

    became

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (flag
    -0.07
    85
    -0.07
     comenz
    -0.06
     chol
    -0.06
    >J
    -0.06
    408
    -0.06
     `.
    -0.06
    Module
    -0.06
    kid
    -0.06
    endtime
    -0.06
    POSITIVE LOGITS
    .obtain
    0.07
    vention
    0.07
    .NODE
    0.06
    				
↵
    0.06
     apro
    0.06
    méně
    0.06
    Issues
    0.06
    _many
    0.06
     Inter
    0.06
    �
    0.06
    Act Density 0.015%

    No Known Activations