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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     altered
    -0.08
    犯罪
    -0.06
     UAE
    -0.06
    ORD
    -0.06
     Olivia
    -0.06
    िसस
    -0.06
    Nat
    -0.06
    	J
    -0.06
     نویس
    -0.06
    економ
    -0.06
    POSITIVE LOGITS
    plaintext
    0.07
    %-
    0.06
     cục
    0.06
    )—
    0.06
    ------------------------------------------------------------------------------------------------
    0.06
     OPS
    0.06
     ngang
    0.06
     initWithFrame
    0.06
    efd
    0.06
     injustice
    0.06
    Act Density 0.001%

    No Known Activations