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

    Neuronpedia

    INDEX
    Explanations

    compiled relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     colo
    0.55
     interoper
    0.50
     rupture
    0.48
     victories
    0.48
     compradores
    0.48
    🇹
    0.47
     seguidores
    0.47
     colaboradores
    0.46
     zwycię
    0.46
     funcionarios
    0.46
    POSITIVE LOGITS
    细
    0.45
    ปล
    0.41
     необхід
    0.41
    細
    0.41
    几年
    0.40
    䀦
    0.40
    Space
    0.40
    必要
    0.40
    Evening
    0.40
    Beer
    0.40
    Act Density 0.005%

    No Known Activations