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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Verg
    -0.06
    โม
    -0.06
     misunderstanding
    -0.06
    .buttons
    -0.06
    ớm
    -0.06
     secured
    -0.06
     rab
    -0.06
    -switch
    -0.06
     scaler
    -0.06
    (seg
    -0.06
    POSITIVE LOGITS
    0.06
     повер
    0.06
    .args
    0.06
    ****↵
    0.06
    .ToDecimal
    0.06
    .EN
    0.06
    羽
    0.06
     tendr
    0.06
    148
    0.06
    odář
    0.06
    Act Density 0.050%

    No Known Activations