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

    Neuronpedia

    INDEX
    Explanations

    overlap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overlap
    -1.18
     overlaps
    -0.99
     overlapped
    -0.91
    overlap
    -0.87
     overlapping
    -0.83
    Overlap
    -0.73
     overla
    -0.64
    StoreMessageInfo
    -0.63
    overlapping
    -0.59
    "]);
    -0.57
    POSITIVE LOGITS
    istar
    0.62
     Wiktionnaire
    0.54
     realisation
    0.54
    Vapour
    0.49
    IGO
    0.49
    rungsseite
    0.48
    Hochspringen
    0.48
    onts
    0.48
    TGF
    0.47
    enegal
    0.47
    Act Density 0.016%

    No Known Activations