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

    Neuronpedia

    INDEX
    Explanations

    explaining things / giving advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     foundational
    0.66
     continual
    0.62
     benefitted
    0.62
     effecting
    0.62
     incrementar
    0.57
     neurologic
    0.57
     interment
    0.56
     advancements
    0.54
     focussed
    0.54
     serendip
    0.53
    POSITIVE LOGITS
     ​​
    0.73
     ?!
    0.72
     !!!
    0.71
    ))))
    0.70
    )))
    0.69
     №
    0.68
     FullHD
    0.67
     XNUMX
    0.66
    .+
    0.65
     conditionally
    0.64
    Act Density 0.005%

    No Known Activations