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

    Neuronpedia

    INDEX
    Explanations

    makeshift/temporary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vœux
    -0.49
    뇨
    -0.48
    föl
    -0.45
     jambes
    -0.45
    caping
    -0.45
     thèmes
    -0.45
     innehå
    -0.45
     oreilles
    -0.44
    ţin
    -0.44
     boisson
    -0.43
    POSITIVE LOGITS
    tonode
    0.71
     виправивши
    0.67
     withal
    0.65
    jspx
    0.63
    tagHelperRunner
    0.62
    WriteBarrier
    0.61
     Winaray
    0.60
    ImageContext
    0.59
     springfox
    0.59
     wisdom
    0.58
    Act Density 0.007%

    No Known Activations