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

    Neuronpedia

    INDEX
    Explanations

    politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iband
    -0.06
    _CLICK
    -0.06
     gib
    -0.06
    ♤
    -0.06
    鹖
    -0.06
    ᠢ
    -0.06
    𝖖
    -0.06
     валют
    -0.06
    �
    -0.06
    碧桂
    -0.06
    POSITIVE LOGITS
     Structural
    0.08
     sus
    0.07
     Sus
    0.07
    もちろん
    0.07
     //"
    0.07
    (Contact
    0.07
    Memory
    0.07
     grips
    0.07
     structural
    0.07
    redo
    0.06
    Act Density 0.290%

    No Known Activations