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

    Neuronpedia

    INDEX
    Explanations

    say quotation mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wor
    -0.07
    Doc
    -0.06
    ários
    -0.06
    мат
    -0.06
    rieving
    -0.06
    ajes
    -0.06
    ded
    -0.06
    ello
    -0.06
    /cpu
    -0.06
    Execute
    -0.06
    POSITIVE LOGITS
     hemp
    0.06
    JKLMNOP
    0.06
     *(*
    0.06
     preventive
    0.06
    (element
    0.06
     objc
    0.06
     seem
    0.06
     hashlib
    0.06
    (Base
    0.06
     Hamm
    0.06
    Act Density 0.005%

    No Known Activations