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

    Neuronpedia

    INDEX
    Explanations

    instructions and recommendations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seuil
    -0.10
    vell
    -0.09
    .Enabled
    -0.08
    issus
    -0.08
    .self
    -0.08
    reshold
    -0.08
    (ct
    -0.08
     chví
    -0.08
    ýs
    -0.08
    .enabled
    -0.08
    POSITIVE LOGITS
     natural
    0.08
     IRC
    0.08
     aproveitar
    0.08
     자연
    0.08
     west
    0.08
    Horm
    0.08
     easier
    0.08
    natural
    0.08
    Natural
    0.07
    自然
    0.07
    Act Density 0.057%

    No Known Activations