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

    Neuronpedia

    INDEX
    Explanations

    what do you like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ாண்டு
    0.42
     বহন
    0.39
    💳
    0.39
    衡量
    0.37
     olduğuna
    0.36
    াপনের
    0.36
     NEEDS
    0.35
    ullan
    0.35
     Concern
    0.34
    лас
    0.34
    POSITIVE LOGITS
    喜欢
    2.27
    喜歡
    2.11
    ชอบ
    2.05
     liking
    1.95
     ชอบ
    1.93
     좋아
    1.88
     liked
    1.88
    喜欢的
    1.88
     좋아하는
    1.80
    喜爱
    1.73
    Act Density 0.024%

    No Known Activations