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

    Neuronpedia

    INDEX
    Explanations

    a/an followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ？？？
    -1.93
     them
    -1.72
     these
    -1.71
    　↓
    -1.65
    ších
    -1.61
     aand
    -1.59
     there
    -1.57
    ～～～
    -1.51
    俢
    -1.49
     chande
    -1.47
    POSITIVE LOGITS
     to
    2.25
     —
    1.95
    —
    1.85
    </h5>
    1.76
     Another
    1.76
    ",
    1.70
     –
    1.69
     fevereiro
    1.64
     You
    1.63
     usual
    1.61
    Act Density 0.092%

    No Known Activations