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

    Neuronpedia

    INDEX
    Explanations

    pubs, taverns, bars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝒕
    2.68
    𝒔
    2.24
    tear
    2.23
    ओ
    2.18
    стью
    2.16
    de
    2.13
    麓
    2.12
    ść
    2.11
    𝒑
    2.10
     contraseña
    2.10
    POSITIVE LOGITS
    ்
    2.57
    ১
    2.54
    an
    2.48
    ../
    2.45
    lname
    2.43
    lishes
    2.38
    ್
    2.37
     вопроса
    2.34
    ic
    2.31
     उससे
    2.25
    Act Density 0.035%

    No Known Activations