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

    Neuronpedia

    INDEX
    Explanations

    de

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ){}↵
    -0.07
    -wise
    -0.07
    -outs
    -0.07
    칠
    -0.06
    	meta
    -0.06
    ticks
    -0.06
     })
    -0.06
    _NUMBER
    -0.06
     declined
    -0.06
     hs
    -0.06
    POSITIVE LOGITS
    onents
    0.07
     fy
    0.06
     precisa
    0.06
     turned
    0.06
     stead
    0.06
     자연
    0.06
    released
    0.06
     splendid
    0.06
    ning
    0.06
    faculty
    0.06
    Act Density 0.090%

    No Known Activations