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

    Neuronpedia

    INDEX
    Explanations

    toy sets and figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bayesian
    0.44
     cittam
    0.44
     hipert
    0.43
     eccentric
    0.41
    ingos
    0.41
     elliptic
    0.40
     algorithmic
    0.40
     Solving
    0.40
    াকৃত
    0.40
     permeate
    0.40
    POSITIVE LOGITS
     miniatures
    1.05
     toys
    0.96
     miniature
    0.94
     dolls
    0.93
     figurines
    0.93
     toy
    0.92
    玩具
    0.92
     doll
    0.90
    Doll
    0.85
     Toys
    0.84
    Act Density 0.239%

    No Known Activations