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

    Neuronpedia

    INDEX
    Explanations

    information sources

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    しまった
    0.51
    VIEW
    0.51
    unst
    0.51
    (".");
    0.49
    IVER
    0.49
    Nev
    0.49
    דה
    0.49
    ذ
    0.48
    ICON
    0.48
    प्र
    0.48
    POSITIVE LOGITS
     brochures
    0.74
     path
    0.71
     brochure
    0.66
     paths
    0.64
     auditions
    0.64
     abi
    0.62
    giphy
    0.61
     prank
    0.61
     Kardash
    0.60
     JPEG
    0.60
    Act Density 0.000%

    No Known Activations