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

    Neuronpedia

    INDEX
    Explanations

    Yes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maneu
    0.76
     употре
    0.74
    .’
    0.73
    .​
    0.69
    .’’
    0.69
    ⁤
    0.68
    󰡕
    0.66
    -​
    0.66
    ::$
    0.65
    .])
    0.65
    POSITIVE LOGITS
    Yes
    0.73
     YES
    0.71
     Yes
    0.70
    YES
    0.70
    見た
    0.66
     नोट
    0.66
    宝石
    0.66
    miot
    0.66
     yes
    0.65
     note
    0.65
    Act Density 0.008%

    No Known Activations