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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Eval
    -0.07
     summons
    -0.07
    �
    -0.06
     문
    -0.06
    ITION
    -0.06
    ุก
    -0.06
    hel
    -0.06
    捕
    -0.06
    十三
    -0.06
     domaine
    -0.06
    POSITIVE LOGITS
     then
    0.07
    ,True
    0.06
     motherboard
    0.06
    "%(
    0.06
    asında
    0.06
     Гер
    0.06
     preserved
    0.06
     listening
    0.06
     Always
    0.06
     rats
    0.06
    Act Density 0.015%

    No Known Activations