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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worthless
    -0.07
     khắc
    -0.07
    oví
    -0.07
    алось
    -0.06
     Мы
    -0.06
    лася
    -0.06
    Branch
    -0.06
     delve
    -0.06
     إليه
    -0.06
    够
    -0.06
    POSITIVE LOGITS
    _at
    0.07
    \core
    0.07
    National
    0.07
     handheld
    0.06
    supplier
    0.06
    NY
    0.06
    _OPER
    0.06
    .encoder
    0.06
    =<?=$
    0.06
    こちら
    0.06
    Act Density 0.158%

    No Known Activations