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

    Neuronpedia

    INDEX
    Explanations

    fundamental

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تخ
    -0.08
    recio
    -0.07
     Serie
    -0.06
    .short
    -0.06
     Tổ
    -0.06
     toprak
    -0.06
    Annotations
    -0.06
    [ch
    -0.06
    ụy
    -0.06
     ihtiy
    -0.06
    POSITIVE LOGITS
    Living
    0.07
    ？」
    0.07
     really
    0.07
     Bolivia
    0.06
     Abraham
    0.06
    loquent
    0.06
    ======
    0.06
    Purple
    0.06
     Ease
    0.06
     Indicates
    0.06
    Act Density 0.001%

    No Known Activations