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

    Neuronpedia

    INDEX
    Explanations

    text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wide
    -0.07
     reinforced
    -0.06
     fec
    -0.06
     traitement
    -0.06
     Mat
    -0.06
     Delegate
    -0.06
     Wide
    -0.06
    ��
    -0.06
     wan
    -0.06
     manoe
    -0.06
    POSITIVE LOGITS
    ima
    0.06
    bird
    0.06
    tur
    0.06
     usted
    0.06
    phrase
    0.06
    :\\
    0.06
     Scotia
    0.06
     xbox
    0.06
    ph
    0.06
    ()}}↵
    0.06
    Act Density 0.238%

    No Known Activations