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

    Neuronpedia

    INDEX
    Explanations

    diverse contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roskov
    -1.10
     referenties
    -1.00
     Baillargeon
    -0.81
     dress
    -0.79
    ViewFeatures
    -0.79
    abytes
    -0.76
     rooftops
    -0.75
     nahilalakip
    -0.75
    Jeografia
    -0.74
    uality
    -0.73
    POSITIVE LOGITS
     sade
    0.44
     investis
    0.42
    6
    0.41
     recommandons
    0.40
    pack
    0.40
    istoitu
    0.40
    HI
    0.39
    8
    0.38
    1
    0.38
    7
    0.38
    Act Density 0.052%

    No Known Activations