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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.77
    qxd
    -0.59
     NUKAT
    -0.59
     Bioaccumulative
    -0.54
    XmlAccessType
    -0.54
    ResumeLayout
    -0.53
    djangoproject
    -0.52
     calendriers
    -0.52
     JpaRepository
    -0.52
    SourceChecksum
    -0.52
    POSITIVE LOGITS
     contribué
    0.51
     }}$,
    0.48
     bleib
    0.46
    ləş
    0.46
    mologie
    0.45
    baarheid
    0.45
    Ivory
    0.45
     voudrais
    0.45
     prisonniers
    0.45
     Hongrie
    0.44
    Act Density 0.001%

    No Known Activations