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
    _response
    -0.07
     QUE
    -0.07
    retty
    -0.06
    UFACT
    -0.06
     QA
    -0.06
    anker
    -0.06
    ucer
    -0.06
     suffer
    -0.06
    .isnan
    -0.06
    .LOGIN
    -0.06
    POSITIVE LOGITS
     Petra
    0.06
     «
    0.06
     confusing
    0.06
    �
    0.06
     Petr
    0.06
     tamamen
    0.06
    Fe
    0.06
     cookie
    0.06
     randomly
    0.06
    »,
    0.06
    Act Density 0.000%

    No Known Activations