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

    Neuronpedia

    INDEX
    Explanations

    beyond

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    레벨
    -0.07
    "]:
    -0.06
     ByteArrayOutputStream
    -0.06
    etiyle
    -0.06
     GM
    -0.06
    Nİ
    -0.06
     Relationships
    -0.06
    IRMWARE
    -0.06
    Skills
    -0.06
    Õ
    -0.06
    POSITIVE LOGITS
    aje
    0.07
    -author
    0.07
    aming
    0.07
     hissed
    0.07
    _epi
    0.07
    loomberg
    0.07
    じ
    0.07
     thwart
    0.06
     αστ
    0.06
    ling
    0.06
    Act Density 0.016%

    No Known Activations