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

    Neuronpedia

    INDEX
    Explanations

    phil

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    평
    -0.08
     выраж
    -0.07
     PYTHON
    -0.07
     trou
    -0.07
    _CHECK
    -0.07
     ['-
    -0.07
    "@
    -0.07
    _SUS
    -0.07
    Ҳ
    -0.07
    עזר
    -0.07
    POSITIVE LOGITS
    염
    0.07
     בלי
    0.07
    0.07
    Omega
    0.07
    альный
    0.07
    erglass
    0.07
     Berm
    0.07
    将成为
    0.07
     acrylic
    0.07
    可能是
    0.07
    Act Density 0.006%

    No Known Activations