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

    Neuronpedia

    INDEX
    Explanations

    Time periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gambar
    -0.07
    Oh
    -0.07
     सभ
    -0.07
    uppen
    -0.06
     Oh
    -0.06
     camb
    -0.06
    ặng
    -0.06
     zahl
    -0.06
    ilerini
    -0.06
     byly
    -0.06
    POSITIVE LOGITS
     Frm
    0.07
    _BY
    0.07
    "/>↵
    0.07
     TN
    0.06
    .validator
    0.06
     GG
    0.06
    WR
    0.06
    SetUp
    0.06
     plano
    0.06
    _VALUE
    0.06
    Act Density 0.057%

    No Known Activations