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

    Neuronpedia

    INDEX
    Explanations

    std

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nasıl
    -0.06
    _positive
    -0.06
    ấp
    -0.06
     범
    -0.06
    )
↵
↵
↵
    -0.06
    edriver
    -0.06
    -slider
    -0.06
    .subtitle
    -0.06
     sürekli
    -0.06
     defe
    -0.06
    POSITIVE LOGITS
     Hogwarts
    0.07
     Supervisor
    0.07
    341
    0.07
    eping
    0.07
     reun
    0.07
     memo
    0.07
     unexpectedly
    0.06
     worthwhile
    0.06
    ually
    0.06
     grain
    0.06
    Act Density 0.000%

    No Known Activations