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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     شود
    -0.07
     한다
    -0.07
    enerate
    -0.07
    اف
    -0.06
     minden
    -0.06
     replaced
    -0.06
    _coord
    -0.06
    .getResult
    -0.06
    щие
    -0.06
    ecedor
    -0.06
    POSITIVE LOGITS
     výstav
    0.08
     โรง
    0.08
    ائه
    0.07
    ські
    0.07
     Pyongyang
    0.07
    @login
    0.07
    );

↵
    0.07
    .databind
    0.07
     {

↵
    0.06
     Při
    0.06
    Act Density 0.008%

    No Known Activations