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

    Neuronpedia

    INDEX
    Explanations

    Name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鄘
    -0.08
     מהמערכת
    -0.07
    NegativeButton
    -0.07
    Degree
    -0.07
    Ữ
    -0.07
    ?v
    -0.07
    React
    -0.07
     Germ
    -0.07
    辩证
    -0.07
     towels
    -0.07
    POSITIVE LOGITS
     rex
    0.07
     것입니다
    0.07
     nostra
    0.07
     Seiten
    0.07
    多くの
    0.07
     justified
    0.07
     Persona
    0.06
    海报
    0.06
     blinds
    0.06
     만약
    0.06
    Act Density 0.001%

    No Known Activations