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

    Neuronpedia

    INDEX
    Explanations

    downstream

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -training
    -0.07
    _TBL
    -0.07
     Calling
    -0.07
     credibility
    -0.07
    _two
    -0.06
    *k
    -0.06
     ск
    -0.06
     thấp
    -0.06
     headquarters
    -0.06
    acie
    -0.06
    POSITIVE LOGITS
    /dom
    0.06
    .onreadystatechange
    0.06
    ayne
    0.06
     delightful
    0.06
     slashes
    0.06
     Zhang
    0.06
    <img
    0.06
     امتی
    0.06
    lbrakk
    0.06
     regarding
    0.06
    Act Density 0.002%

    No Known Activations