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

    Neuronpedia

    INDEX
    Explanations

    Adapter

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    奢侈品
    -0.07
    袷
    -0.07
     VIII
    -0.07
    敬请
    -0.07
    adresse
    -0.07
    充满
    -0.06
    ไอ
    -0.06
     espos
    -0.06
     erectile
    -0.06
    𝓘
    -0.06
    POSITIVE LOGITS
    .country
    0.07
    乌鲁木齐
    0.07
    纂
    0.07
    0.06
    	sb
    0.06
    ointment
    0.06
     TY
    0.06
     тор
    0.06
     survey
    0.06
    <Resource
    0.06
    Act Density 0.001%

    No Known Activations