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

    Neuronpedia

    INDEX
    Explanations

    animated lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _s
    -0.07
     ^
    -0.07
    AG
    -0.07
    �
    -0.07
     বিস
    -0.07
     the
    -0.07
    AB
    -0.07
    切
    -0.07
    LA
    -0.07
    igh
    -0.07
    POSITIVE LOGITS
     esteve
    0.09
    ്യേ
    0.09
     classics
    0.09
    ियल
    0.08
     дұ
    0.08
    buquerque
    0.08
     fecha
    0.08
    /Card
    0.08
     zwangers
    0.08
     Cardinals
    0.08
    Act Density 0.168%

    No Known Activations