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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pev
    -0.07
     terrible
    -0.06
     mujer
    -0.06
     confessed
    -0.06
     FIRE
    -0.06
    /swagger
    -0.06
     Callback
    -0.06
     Wrapper
    -0.06
     suche
    -0.06
    	synchronized
    -0.06
    POSITIVE LOGITS
    -to
    0.07
     without
    0.07
    minated
    0.07
     TO
    0.07
    InMillis
    0.06
     absent
    0.06
     "
↵
    0.06
    [t
    0.06
     نب
    0.06
     Cleanup
    0.06
    Act Density 0.008%

    No Known Activations