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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    итай
    -0.08
     رز
    -0.07
    >(),
    -0.06
    .swt
    -0.06
     spanning
    -0.06
    ForEach
    -0.06
    .Texture
    -0.06
    Weapon
    -0.06
    _cond
    -0.06
    신청
    -0.06
    POSITIVE LOGITS
    çuk
    0.07
    」↵
    0.06
    》↵
    0.06
     sẵn
    0.06
    "G
    0.06
     }>↵
    0.06
     standpoint
    0.06
     retaliation
    0.06
    _SIZE
    0.06
    !'↵
    0.06
    Act Density 0.013%

    No Known Activations