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

    Neuronpedia

    INDEX
    Explanations

    specific names and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Orig
    0.39
     göz
    0.38
    Growing
    0.38
     chilling
    0.38
    生长
    0.38
    YO
    0.37
     गैस
    0.36
    YEAR
    0.36
     groei
    0.36
    year
    0.36
    POSITIVE LOGITS
     FV
    0.43
     HV
    0.43
     Hv
    0.43
    Cv
    0.43
     pv
    0.42
     бъде
    0.42
     become
    0.41
     hv
    0.40
     BV
    0.40
    rugada
    0.40
    Act Density 0.000%

    No Known Activations