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

    Neuronpedia

    INDEX
    Explanations

    Currency abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    importe
    -0.07
     homme
    -0.07
     serving
    -0.07
    refund
    -0.07
    rito
    -0.06
    _UNIT
    -0.06
    ockets
    -0.06
     allegations
    -0.06
     HTTP
    -0.06
     رز
    -0.06
    POSITIVE LOGITS
     JSBracketAccess
    0.07
     Nẵng
    0.07
     교
    0.07
    اوية
    0.07
     Льв
    0.06
     /*<<<
    0.06
     HIM
    0.06
    ，同时
    0.06
     yyn
    0.06
     SVC
    0.06
    Act Density 0.012%

    No Known Activations