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

    Neuronpedia

    INDEX
    Explanations

    learn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Total
    -0.08
    Approx
    -0.07
    anism
    -0.07
    客
    -0.07
    (Abstract
    -0.06
    REL
    -0.06
    Timeline
    -0.06
     Quint
    -0.06
     Σα
    -0.06
     Pl
    -0.06
    POSITIVE LOGITS
    "){↵
    0.07
     }):
    0.06
    0.06
    óz
    0.06
    去
    0.06
    ={↵
    0.06
    技術
    0.06
    issing
    0.06
     smarty
    0.06
    iframe
    0.06
    Act Density 0.015%

    No Known Activations