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

    Neuronpedia

    INDEX
    Explanations

    binder clip, binder jetting, binder environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bind
    0.40
     xm
    0.40
     बंध
    0.38
     sparrow
    0.38
    Xiao
    0.37
    屹
    0.37
    ン
    0.36
    pca
    0.36
    बंध
    0.35
     observed
    0.35
    POSITIVE LOGITS
     Allowance
    0.39
    ва
    0.39
    ক্তির
    0.37
    鲷
    0.37
     trackers
    0.36
     Fudge
    0.36
    Block
    0.35
    鏘
    0.35
     ব্রিগে
    0.35
    鏻
    0.35
    Act Density 0.001%

    No Known Activations