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

    Neuronpedia

    INDEX
    Explanations

    distance and direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鹖
    0.46
    ྵ
    0.46
    ྣ
    0.45
    ྨ
    0.44
     decept
    0.44
    ংস
    0.43
    ྫ
    0.43
     bolted
    0.43
    𝘬
    0.43
    0.42
    POSITIVE LOGITS
    s
    0.64
    sig
    0.51
    unities
    0.50
    yj
    0.49
    ut
    0.49
    roi
    0.48
    ene
    0.47
    ej
    0.46
    ts
    0.46
    o
    0.46
    Act Density 0.000%

    No Known Activations