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

    Neuronpedia

    INDEX
    Explanations

    світло

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ivate
    0.41
    alled
    0.40
     universality
    0.40
     adhered
    0.37
     scarcity
    0.37
    เรีย
    0.37
     retrofit
    0.36
     Sticks
    0.36
     होऊ
    0.36
    rein
    0.35
    POSITIVE LOGITS
    лана
    0.75
    lana
    0.64
    λο
    0.59
    LO
    0.57
     Svet
    0.55
    lovl
    0.55
    ło
    0.54
    лови
    0.53
    loh
    0.53
    lo
    0.53
    Act Density 0.001%

    No Known Activations