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

    Neuronpedia

    INDEX
    Explanations

    lord of the rings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Là
    0.53
    ân
    0.47
    춤
    0.46
    igui
    0.45
    ધુ
    0.44
     Cette
    0.43
     tươi
    0.43
     Dye
    0.43
     Bonne
    0.41
    iguation
    0.41
    POSITIVE LOGITS
     terror
    0.47
    :<
    0.47
     empathy
    0.46
    енты
    0.46
     empathetic
    0.46
     initiate
    0.45
    パワー
    0.45
    import
    0.44
     power
    0.44
    ERIC
    0.44
    Act Density 0.005%

    No Known Activations