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

    Neuronpedia

    INDEX
    Explanations

    exchange rates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     explosive
    -0.07
    房贷
    -0.07
    兹
    -0.06
     sprawling
    -0.06
    �
    -0.06
     đẩ
    -0.06
     amid
    -0.06
     ITV
    -0.06
     **↵
    -0.06
    etti
    -0.06
    POSITIVE LOGITS
    细心
    0.07
    icipants
    0.07
     respondsToSelector
    0.07
    🛠
    0.07
    곰
    0.07
    늄
    0.07
    ƈ
    0.07
     Nin
    0.07
    kernel
    0.07
    朴实
    0.07
    Act Density 0.007%

    No Known Activations