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

    Neuronpedia

    INDEX
    Explanations

    text editing/generation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Armor
    -0.08
    កម្ម
    -0.08
    <header
    -0.07
    (inst
    -0.07
     conseillé
    -0.07
     Inform
    -0.07
     informar
    -0.07
     investments
    -0.07
     cortical
    -0.07
    roi
    -0.07
    POSITIVE LOGITS
     trailing
    0.12
     koń
    0.10
    .endswith
    0.10
    最後
    0.10
    尾
    0.09
    ท้าย
    0.09
    Suffix
    0.09
     конце
    0.09
    _SUFFIX
    0.09
    最后
    0.09
    Act Density 0.069%

    No Known Activations