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

    Neuronpedia

    INDEX
    Explanations

    author and date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    discord
    0.39
    COPY
    0.37
     subgoal
    0.36
    стром
    0.35
    ENSATION
    0.35
    OEt
    0.34
    要
    0.34
    ತಕ್ಕ
    0.34
     angle
    0.33
    +[
    0.33
    POSITIVE LOGITS
     admin
    1.13
     Admin
    1.03
    admin
    0.95
     Posted
    0.94
    Posted
    0.93
     posted
    0.90
     Blog
    0.88
    Admin
    0.86
     blog
    0.82
    posted
    0.79
    Act Density 0.000%

    No Known Activations