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

    Neuronpedia

    INDEX
    Explanations

    format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ουσ
    -0.07
     kh
    -0.07
     expensive
    -0.07
    ,m
    -0.07
    _validator
    -0.06
    �
    -0.06
     جلس
    -0.06
     slow
    -0.06
     hauling
    -0.06
     aur
    -0.06
    POSITIVE LOGITS
     />
↵
    0.06
    (year
    0.06
    anteed
    0.06
    ">
↵
    0.06
    _long
    0.06
    -.
    0.06
     LAW
    0.05
     *}↵↵
    0.05
    _RENDERER
    0.05
    腾
    0.05
    Act Density 0.061%

    No Known Activations