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

    Neuronpedia

    INDEX
    Explanations

    how you feel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ర
    0.54
    σεις
    0.53
     löyty
    0.50
     erad
    0.50
    ბ
    0.49
     entice
    0.48
    unlist
    0.48
     getValue
    0.46
     coincid
    0.46
     źród
    0.46
    POSITIVE LOGITS
    AP
    0.36
     मन
    0.36
    ยนต์
    0.36
    रोना
    0.35
    आर
    0.35
     Lent
    0.34
    als
    0.33
    naire
    0.33
    lar
    0.33
    BeanFactory
    0.33
    Act Density 0.172%

    No Known Activations