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

    Neuronpedia

    INDEX
    Explanations

    developer topics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     VCO
    0.65
     ава
    0.64
     inventors
    0.61
     inquis
    0.59
     ita
    0.59
     AVR
    0.59
     datar
    0.59
    淘
    0.59
     breakers
    0.59
     BAS
    0.58
    POSITIVE LOGITS
     části
    0.54
     Verantwortung
    0.54
     വൃ
    0.52
    Vorlage
    0.52
    Handle
    0.51
    ிறு
    0.51
     transición
    0.51
     součas
    0.51
    ={()=>
    0.51
    GraphicsUnit
    0.51
    Act Density 0.000%

    No Known Activations