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

    Neuronpedia

    INDEX
    Explanations

    continuous

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     burgl
    -0.07
    \Php
    -0.06
     descricao
    -0.06
     Plato
    -0.06
     nghiệm
    -0.06
    dates
    -0.06
     Roh
    -0.06
     principals
    -0.06
     unparalleled
    -0.06
     北
    -0.06
    POSITIVE LOGITS
    _mc
    0.07
     kolem
    0.07
     lur
    0.07
     갖
    0.07
     궁금
    0.07
     quaternion
    0.06
     SQLAlchemy
    0.06
     resize
    0.06
     пла
    0.06
     платеж
    0.06
    Act Density 0.027%

    No Known Activations