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

    Neuronpedia

    INDEX
    Explanations

    description

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .yang
    -0.07
    _IT
    -0.07
     losses
    -0.07
    .sendStatus
    -0.07
    -hearted
    -0.07
    .compress
    -0.06
    tran
    -0.06
    thinking
    -0.06
    imag
    -0.06
     gases
    -0.06
    POSITIVE LOGITS
     downside
    0.07
     CD
    0.07
    Canon
    0.06
     pdf
    0.06
    .Not
    0.06
    destruct
    0.06
     dengan
    0.06
    advance
    0.06
    ิทยาศาสตร
    0.06
     classic
    0.06
    Act Density 0.004%

    No Known Activations