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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    วน
    -0.07
     답변
    -0.07
     سع
    -0.07
    !");
↵
    -0.07
    <textarea
    -0.07
    贸
    -0.06
    -Sep
    -0.06
    addock
    -0.06
     briefed
    -0.06
    _accum
    -0.06
    POSITIVE LOGITS
    Nova
    0.06
    ματος
    0.06
    fter
    0.06
     cerr
    0.06
    aders
    0.06
    ků
    0.06
    ской
    0.06
    metics
    0.06
     =>
    0.06
     wears
    0.06
    Act Density 0.048%

    No Known Activations