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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _team
    -0.07
    (tweet
    -0.07
    )");↵↵
    -0.06
     Wash
    -0.06
    Applications
    -0.06
    .rec
    -0.06
    (ad
    -0.06
     Reward
    -0.06
     username
    -0.06
    ращ
    -0.06
    POSITIVE LOGITS
     땅
    0.07
    ]!='
    0.07
     обла
    0.06
    oq
    0.06
     ++)
    0.06
     QtGui
    0.06
    했다
    0.06
    .omg
    0.06
    vasion
    0.06
    LTR
    0.06
    Act Density 0.005%

    No Known Activations