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
    out
    -0.07
     QMap
    -0.07
    기는
    -0.07
     plastics
    -0.07
    OUT
    -0.07
    該
    -0.07
     Marty
    -0.06
     prohib
    -0.06
    exit
    -0.06
    ـل
    -0.06
    POSITIVE LOGITS
    Constructed
    0.07
     функ
    0.06
    tv
    0.06
     hairstyle
    0.06
    _rom
    0.06
    persist
    0.06
    _PTR
    0.06
    _EXPR
    0.06
     dreadful
    0.06
    olleyError
    0.06
    Act Density 0.018%

    No Known Activations