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

    Neuronpedia

    INDEX
    Explanations

    <|start|>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sm
    -0.07
    -0.07
    cko
    -0.07
     ethnic
    -0.07
     talent
    -0.07
    dl
    -0.07
     talents
    -0.06
    Salut
    -0.06
     תיק
    -0.06
    aven
    -0.06
    POSITIVE LOGITS
     consequences
    0.15
     consequências
    0.13
     последствия
    0.12
     repercussions
    0.11
     consecuencias
    0.11
     conséquences
    0.11
     ماذا
    0.11
     consequence
    0.10
     ramifications
    0.10
     gevolgen
    0.10
    Act Density 0.059%
    No Known Activations