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

    Neuronpedia

    INDEX
    Explanations

    Training/preparation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     quizzes
    -0.06
    _MAXIMUM
    -0.06
    _ATTACK
    -0.06
    _appro
    -0.06
     Lịch
    -0.06
     Pony
    -0.06
    orent
    -0.06
    	Page
    -0.06
     When
    -0.06
    POSITIVE LOGITS
     WS
    0.07
     hosp
    0.07
    圭
    0.07
     intimate
    0.06
    Along
    0.06
    enson
    0.06
    erva
    0.06
     LSU
    0.06
    VERBOSE
    0.06
    ]\\
    0.06
    Act Density 0.088%

    No Known Activations