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

    Neuronpedia

    INDEX
    Explanations

    code structures or errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coniferous
    0.30
     conductance
    0.30
    walls
    0.28
     craftsmen
    0.27
    ometrical
    0.26
     rarer
    0.26
    vertical
    0.26
    erian
    0.26
     carbonates
    0.26
    okon
    0.25
    POSITIVE LOGITS
     Использу
    0.38
     Created
    0.36
    Copyright
    0.35
     Description
    0.34
     github
    0.33
     GitHub
    0.33
     Copyright
    0.32
     Github
    0.32
     Using
    0.31
     Initialize
    0.31
    Act Density 0.003%

    No Known Activations