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

    Neuronpedia

    INDEX
    Explanations

    Excerpts from various documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evolves
    -0.07
    .NoError
    -0.06
    文献
    -0.06
     ιστο
    -0.06
     filmmaker
    -0.06
    ario
    -0.06
    ойчив
    -0.06
    běh
    -0.06
    νομ
    -0.06
    '},
    -0.05
    POSITIVE LOGITS
     advantages
    0.07
     hiçbir
    0.07
    Searching
    0.07
    (img
    0.07
     patient
    0.06
    scheduler
    0.06
     deterioration
    0.06
    Containing
    0.06
    ANTED
    0.06
    isol
    0.06
    Act Density 0.000%

    No Known Activations