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

    Neuronpedia

    INDEX
    Explanations

    date object creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etc
    0.90
    ㅋㅋ
    0.87
    看法
    0.86
     délais
    0.85
     ㅋㅋ
    0.85
     Etc
    0.83
    などは
    0.82
    ㅋ
    0.81
     Macs
    0.81
     joked
    0.81
    POSITIVE LOGITS
     amely
    0.95
     homogeneous
    0.94
     సంవత్సర
    0.87
     welcher
    0.86
     welche
    0.85
     perteneciente
    0.85
     mellitus
    0.84
     cardiovascular
    0.84
     physicochemical
    0.84
     homogenous
    0.84
    Act Density 0.242%

    No Known Activations