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

    Neuronpedia

    INDEX
    Explanations

    linux sudo apt install

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Git
    0.36
     YAML
    0.34
     entries
    0.31
    Git
    0.31
     registries
    0.31
     DOM
    0.30
     entry
    0.29
     execute
    0.29
     registry
    0.29
    std
    0.28
    POSITIVE LOGITS
    zechoslovakia
    0.31
    憉
    0.30
    罡
    0.30
     ostrich
    0.29
    Methyl
    0.29
    linux
    0.29
    軹
    0.29
    ガラ
    0.29
    ropath
    0.29
    து
    0.28
    Act Density 0.009%

    No Known Activations