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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AUTO
    -0.06
     نیر
    -0.06
     detectors
    -0.06
     春
    -0.06
    _STYLE
    -0.06
    �
    -0.06
    _even
    -0.06
     band
    -0.06
    ュー
    -0.06
    ため
    -0.06
    POSITIVE LOGITS
     cognitive
    0.07
    -comment
    0.07
     interfaces
    0.07
    퇴
    0.06
     Chronicle
    0.06
     getElement
    0.06
     setLoading
    0.06
    \Helper
    0.06
     set
    0.06
     अभ
    0.06
    Act Density 0.001%

    No Known Activations