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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARIANT
    -0.07
    LING
    -0.07
    ệt
    -0.07
    ADATA
    -0.07
     Percy
    -0.07
     pigeon
    -0.07
    $is
    -0.07
    屋子
    -0.07
    _digest
    -0.07
     rehabilitation
    -0.07
    POSITIVE LOGITS
     rab
    0.08
    ㈰
    0.07
    맘
    0.07
    Ꭿ
    0.07
    旮
    0.07
    .compose
    0.07
    向记者
    0.07
    ائد
    0.07
     RESPONS
    0.07
    唝
    0.07
    Act Density 0.074%

    No Known Activations