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

    Neuronpedia

    INDEX
    Explanations

    informal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    际
    -0.07
    ως
    -0.06
    Sid
    -0.06
    GT
    -0.06
    LEM
    -0.05
     QLD
    -0.05
    acas
    -0.05
    eterangan
    -0.05
    _adc
    -0.05
     MutableList
    -0.05
    POSITIVE LOGITS
     đủ
    0.07
     margin
    0.07
    рин
    0.07
     законом
    0.07
     Programming
    0.07
    ğinde
    0.07
     Moving
    0.07
     confined
    0.07
    .grid
    0.06
    urally
    0.06
    Act Density 0.002%

    No Known Activations