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

    Neuronpedia

    INDEX
    Explanations

    diced

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mah
    -0.07
    cepts
    -0.07
    世纪
    -0.07
    _fifo
    -0.07
     ignorant
    -0.07
    rence
    -0.07
     Grand
    -0.06
     We
    -0.06
    _nl
    -0.06
    anguages
    -0.06
    POSITIVE LOGITS
     ime
    0.07
    <|endoftext|>
    0.07
    UserCode
    0.07
    为例
    0.07
     الحمل
    0.07
    zá
    0.07
    iju
    0.06
     snug
    0.06
    ].↵
    0.06
    送料
    0.06
    Act Density 0.007%

    No Known Activations