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

    Neuronpedia

    INDEX
    Explanations

    word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    1.78
    y
    1.73
    M
    1.59
    ن
    1.39
    ي
    1.38
    T
    1.34
    U
    1.32
    X
    1.32
    l
    1.31
    i
    1.30
    POSITIVE LOGITS
    <0x07>
    0.89
    <unused371>
    0.84
     comorbidities
    0.83
    <unused2041>
    0.83
    
    0.82
    <unused407>
    0.82
    <unused506>
    0.81
    <unused1073>
    0.81
    ;
    0.80
    <unused581>
    0.80
    Act Density 0.951%

    No Known Activations