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

    Neuronpedia

    INDEX
    Explanations

    dialogue markers and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    L
    0.59
     strives
    0.59
     J
    0.59
    J
    0.57
     n
    0.56
     il
    0.56
     strive
    0.55
     ngày
    0.53
     L
    0.51
     những
    0.51
    POSITIVE LOGITS
    옇
    0.71
     Quadrupèdes
    0.66
     మీకు
    0.65
    ಿಸುತ್ತ
    0.64
     StandardScaler
    0.63
    தலாக
    0.62
    ákat
    0.62
    蟶
    0.61
    ៉ុ
    0.61
    𝚙
    0.61
    Act Density 0.001%

    No Known Activations