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

    Neuronpedia

    INDEX
    Explanations

    jewel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ROM
    -0.08
    问责
    -0.07
     kilomet
    -0.07
     strapon
    -0.07
    iculos
    -0.07
     closely
    -0.07
    _nonce
    -0.07
    起义
    -0.06
     Cly
    -0.06
    片面
    -0.06
    POSITIVE LOGITS
    =get
    0.07
     treffen
    0.06
    trägt
    0.06
    荣
    0.06
     ­
    0.06
     PCR
    0.06
    가
    0.06
    阻
    0.06
    妨
    0.06
    Expl
    0.06
    Act Density 0.038%

    No Known Activations