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

    Neuronpedia

    INDEX
    Explanations

    say "2"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    conomic
    -0.08
    💔
    -0.08
    🚪
    -0.07
    conom
    -0.07
    ♕
    -0.07
    Ē
    -0.07
    Visit
    -0.07
    𝓜
    -0.07
    .Score
    -0.07
     reopening
    -0.07
    POSITIVE LOGITS
    dns
    0.07
     Nylon
    0.07
    .Sm
    0.07
     disparity
    0.07
     Genius
    0.07
    ael
    0.06
    ﾄ
    0.06
     seu
    0.06
     Crystal
    0.06
    尼亚
    0.06
    Act Density 0.008%

    No Known Activations