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

    Neuronpedia

    INDEX
    Explanations

    news and information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     how
    -0.07
    bras
    -0.07
     her
    -0.06
    graduate
    -0.06
     HIM
    -0.06
    	ASSERT
    -0.06
    ELY
    -0.06
    mnt
    -0.06
    ocoder
    -0.06
     評
    -0.06
    POSITIVE LOGITS
     Abd
    0.07
     kannst
    0.06
    _cm
    0.06
     UIP
    0.06
     Swiss
    0.06
     Hund
    0.06
    _bo
    0.06
    _audit
    0.06
     варт
    0.06
     akt
    0.06
    Act Density 0.391%

    No Known Activations