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
    Sans
    -0.07
     newUser
    -0.07
     있
    -0.06
    \Modules
    -0.06
     allies
    -0.06
     tanım
    -0.06
     lain
    -0.06
     Removes
    -0.06
     pantalla
    -0.06
    ran
    -0.06
    POSITIVE LOGITS
    /by
    0.07
    ....↵↵
    0.07
     rid
    0.06
    Mit
    0.06
    %',
    0.06
    _Check
    0.06
     действ
    0.06
    طة
    0.06
    =temp
    0.06
    ....
    0.06
    Act Density 0.223%

    No Known Activations