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

    Neuronpedia

    INDEX
    Explanations

    direct

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    觉
    -0.07
    ากร
    -0.06
     TypeInfo
    -0.06
     актив
    -0.06
     thẩm
    -0.06
    .Creator
    -0.06
    浩
    -0.06
     olig
    -0.06
    안마
    -0.06
    Solid
    -0.06
    POSITIVE LOGITS
     consultation
    0.07
     isArray
    0.07
     Genetics
    0.06
     Lieutenant
    0.06
     Jae
    0.06
    utenant
    0.06
    <any
    0.06
     minist
    0.06
     rele
    0.06
     Jackets
    0.06
    Act Density 0.011%

    No Known Activations