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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CHANGE
    -0.07
     đông
    -0.07
     ठ
    -0.06
    ATS
    -0.06
     "@"
    -0.06
    	instance
    -0.06
    ену
    -0.06
     Private
    -0.06
    _voice
    -0.06
     PRIVATE
    -0.06
    POSITIVE LOGITS
    -reaching
    0.07
    /order
    0.07
     पढ
    0.07
    Working
    0.07
    VG
    0.06
    füg
    0.06
    WithValue
    0.06
    �ng
    0.06
     drug
    0.06
    _username
    0.06
    Act Density 0.001%

    No Known Activations