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

    Neuronpedia

    INDEX
    Explanations

    lectric

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bazı
    -0.08
    科普
    -0.07
     thoughtful
    -0.07
     aşağıd
    -0.07
    🦒
    -0.07
    עוד
    -0.07
     Applicants
    -0.07
    车内
    -0.07
    __.
    -0.07
    dden
    -0.07
    POSITIVE LOGITS
     ))↵
    0.08
    );
↵
↵
↵
    0.08
     ");
↵
    0.07
    acity
    0.07
    _roll
    0.07
    会产生
    0.07
    	global
    0.07
     Degrees
    0.07
    _Ent
    0.07
     ';↵
    0.06
    Act Density 0.001%

    No Known Activations