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

    Neuronpedia

    INDEX
    Explanations

    Brill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🏴
    -0.08
    ♠
    -0.07
    AGON
    -0.07
    ﾑ
    -0.07
    .tv
    -0.07
     cx
    -0.07
     swung
    -0.07
    此
    -0.07
     telephone
    -0.07
     SAVE
    -0.07
    POSITIVE LOGITS
    arte
    0.08
     hormonal
    0.08
    Uno
    0.07
    回
    0.07
     Lew
    0.07
     Premiere
    0.07
     Romero
    0.07
    ardware
    0.07
    Oregon
    0.07
    arl
    0.07
    Act Density 0.003%

    No Known Activations