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

    Neuronpedia

    INDEX
    Explanations

    uses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sovereignty
    -0.08
     Aquarius
    -0.08
     cres
    -0.08
     Vim
    -0.08
     პროგრამ
    -0.08
     Renaissance
    -0.08
     AAA
    -0.08
     рест
    -0.08
     Tess
    -0.08
     thriller
    -0.08
    POSITIVE LOGITS
     during
    0.12
    During
    0.12
     During
    0.11
    during
    0.11
     durante
    0.09
     während
    0.09
     tijdens
    0.09
     modalità
    0.09
    Tijdens
    0.09
     temporarily
    0.09
    Act Density 0.003%

    No Known Activations