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

    Neuronpedia

    INDEX
    Explanations

    pushing an object or goal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    2.18
    тус
    2.13
    ة
    2.11
    etku
    2.03
    za
    2.03
     encarg
    2.02
    jLabel
    1.98
    bs
    1.97
    elon
    1.94
    л
    1.94
    POSITIVE LOGITS
    ра
    3.38
    y
    3.19
    s
    2.66
    تر
    2.63
    ן
    2.56
     proteomics
    2.56
    ים
    2.52
    n
    2.48
    ना
    2.42
     condimentum
    2.38
    Act Density 0.205%

    No Known Activations