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
    �
    -0.06
     (\
    -0.06
    -0.06
    (rc
    -0.06
    	Client
    -0.06
    (struct
    -0.06
    %)
    -0.06
     Claire
    -0.06
     erót
    -0.06
     Ancak
    -0.06
    POSITIVE LOGITS
     TYPO
    0.07
    fail
    0.07
    PCI
    0.07
     Overflow
    0.07
    IMPORT
    0.07
     Alarm
    0.07
    FAIL
    0.06
    ──
    0.06
    виг
    0.06
     ration
    0.06
    Act Density 0.012%

    No Known Activations