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

    Neuronpedia

    INDEX
    Explanations

    code snippets values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     denaturation
    0.56
     intravenously
    0.55
     mottled
    0.53
     phosphorylated
    0.51
     imidazole
    0.51
    gmzy
    0.51
     nymphs
    0.50
     calving
    0.50
     सूजन
    0.50
     Elektrokhimiya
    0.49
    POSITIVE LOGITS
    _
    0.57
    json
    0.53
    replace
    0.52
    r
    0.52
    s
    0.52
    nan
    0.51
    array
    0.51
    text
    0.50
    0.49
    title
    0.48
    Act Density 0.015%

    No Known Activations