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

    Neuronpedia

    INDEX
    Explanations

    urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wood
    0.19
    Use
    0.19
     Use
    0.19
     Time
    0.18
     bedside
    0.18
    Loss
    0.18
     Iowa
    0.17
     thoughtful
    0.17
    ﻂ
    0.17
     gentle
    0.17
    POSITIVE LOGITS
     sarees
    0.27
     internazionale
    0.24
     netizens
    0.23
     tweepy
    0.23
     Datuk
    0.23
     Pooja
    0.23
    瞋
    0.22
     internasional
    0.22
     ruining
    0.22
    aadhar
    0.22
    Act Density 0.007%

    No Known Activations