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

    Neuronpedia

    INDEX
    Explanations

    .hpp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	restore
    -0.06
    .format
    -0.06
     BITS
    -0.06
    Tell
    -0.06
     Day
    -0.06
    _age
    -0.06
     Пол
    -0.06
    Encoding
    -0.06
     buổi
    -0.06
    ,:
    -0.05
    POSITIVE LOGITS
     />}↵
    0.08
     poss
    0.07
     responsibilities
    0.07
     }
↵
↵
    0.07
     candidate
    0.07
     boss
    0.06
    elfth
    0.06
    VE
    0.06
     narr
    0.06
     April
    0.06
    Act Density 0.004%

    No Known Activations