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

    Neuronpedia

    INDEX
    Explanations

    words like level or neural

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ἠ
    0.44
     visto
    0.44
    ल्पना
    0.42
     viste
    0.38
    ிற்ப
    0.38
    ungsseite
    0.37
     vista
    0.37
    蛻
    0.36
    র্ষ
    0.36
    unculus
    0.36
    POSITIVE LOGITS
    EOUS
    0.40
     gloves
    0.38
     warms
    0.38
    ेंबर
    0.37
     warm
    0.37
     meilleures
    0.37
    enged
    0.36
    Change
    0.36
     warming
    0.36
    pegno
    0.36
    Act Density 0.000%

    No Known Activations