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

    Neuronpedia

    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     revolutions
    -0.07
     decl
    -0.07
     Kot
    -0.07
    홀
    -0.07
    Presence
    -0.07
    _Val
    -0.07
     Kab
    -0.06
    _DETECT
    -0.06
    shouldReceive
    -0.06
    沈
    -0.06
    POSITIVE LOGITS
    uetype
    0.07
    	CG
    0.06
    ूरत
    0.06
     titten
    0.06
    .isActive
    0.06
     IntelliJ
    0.06
    ******↵↵
    0.06
    .Green
    0.06
     Online
    0.06
    .online
    0.06
    Act Density 0.001%

    No Known Activations