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

    Neuronpedia

    INDEX
    Explanations

    one topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vastly
    0.51
     effecting
    0.49
     continual
    0.46
     focussed
    0.46
     underneath
    0.46
     应用
    0.44
     benefitted
    0.44
     lessened
    0.43
     continually
    0.42
     effected
    0.42
    POSITIVE LOGITS
     rapproche
    0.57
     (!)
    0.55
     XNUMX
    0.54
     manifestations
    0.53
     analogues
    0.52
     ​​
    0.52
     peculiarities
    0.50
     neoplasms
    0.50
     analogs
    0.47
     manipulations
    0.46
    Act Density 0.004%

    No Known Activations