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

    Neuronpedia

    INDEX
    Explanations

    birch trees and bark

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.99
    an
    0.75
    i
    0.75
    l
    0.68
     anonym
    0.61
    el
    0.60
    ה
    0.60
     victory
    0.58
     gout
    0.57
    er
    0.57
    POSITIVE LOGITS
    с
    0.60
    보다
    0.58
    因而
    0.54
    со
    0.53
    𝐛
    0.53
    ᱭ
    0.50
    моль
    0.50
    စ
    0.50
     работы
    0.48
    හර
    0.48
    Act Density 0.001%

    No Known Activations