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

    Neuronpedia

    INDEX
    Explanations

    providing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outputStream
    -0.07
     Klaus
    -0.07
    .forChild
    -0.07
     airflow
    -0.07
     inhal
    -0.07
    itez
    -0.06
     overdose
    -0.06
    (IF
    -0.06
    ihn
    -0.06
     luk
    -0.06
    POSITIVE LOGITS
     Courts
    0.07
     Ranger
    0.06
     THEM
    0.06
    ема
    0.06
    Mismatch
    0.06
    _CONST
    0.06
     Jamie
    0.06
     NAMES
    0.06
    AntiForgeryToken
    0.06
     Playing
    0.06
    Act Density 0.219%

    No Known Activations