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

    Neuronpedia

    INDEX
    Explanations

    Android Auto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MEP
    0.53
     Igual
    0.52
     эмне
    0.52
     Optimized
    0.51
     forfait
    0.50
     Meille
    0.48
     Alles
    0.48
     Seç
    0.47
     Wettbewer
    0.47
    σουν
    0.47
    POSITIVE LOGITS
    GFR
    0.43
    ৃদ্ধ
    0.43
    Fuj
    0.42
    ͠
    0.42
    emerg
    0.42
    heet
    0.41
    ㄧ
    0.40
    亟
    0.40
    CTION
    0.40
    glio
    0.40
    Act Density 0.001%

    No Known Activations