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

    Neuronpedia

    INDEX
    Explanations

    version numbers and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     배열
    -0.07
     alive
    -0.07
     ---↵
    -0.07
    (resolve
    -0.07
     Parents
    -0.06
     magnets
    -0.06
     ngăn
    -0.06
    [],↵
    -0.06
     CharSequence
    -0.06
    __
↵
    -0.06
    POSITIVE LOGITS
     кри
    0.07
    _meta
    0.06
    -res
    0.06
    Organization
    0.06
    %A
    0.06
     краї
    0.06
    ли
    0.06
    _encode
    0.06
     mutil
    0.06
    -properties
    0.06
    Act Density 0.086%

    No Known Activations