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
    CENT
    -0.07
     Öz
    -0.07
     tn
    -0.07
    �
    -0.06
     mosquito
    -0.06
     move
    -0.06
    /doc
    -0.06
     clue
    -0.06
     fibers
    -0.06
     gray
    -0.06
    POSITIVE LOGITS
    )+
    0.13
    ]+\
    0.13
    )-
    0.12
    ()+
    0.11
    ))+
    0.11
    )*(
    0.10
    ]*
    0.10
    }_{
    0.10
    )*
    0.10
    )!↵
    0.10
    Act Density 0.075%

    No Known Activations