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
     Oktober
    -0.07
     vej
    -0.06
    状况
    -0.06
     hairst
    -0.06
     tg
    -0.06
    %(
    -0.06
     HttpStatusCodeResult
    -0.06
     uvědom
    -0.06
     mohou
    -0.06
     gon
    -0.06
    POSITIVE LOGITS
    lice
    0.06
     lever
    0.06
    -pages
    0.06
    _centers
    0.06
    TimeStamp
    0.06
    lene
    0.06
    zung
    0.06
     discriminatory
    0.06
     cute
    0.06
    structures
    0.06
    Act Density 0.008%

    No Known Activations