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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    钱
    0.76
     مجال
    0.70
    ulti
    0.70
    íd
    0.68
    zię
    0.68
    さて
    0.67
    vik
    0.66
    accessibility
    0.65
    ueva
    0.65
    plied
    0.65
    POSITIVE LOGITS
     bumble
    0.92
     beta
    0.92
     gamma
    0.90
     le
    0.84
     Beta
    0.83
     petting
    0.81
     bomber
    0.80
     dreamy
    0.80
    antom
    0.79
     hedgehog
    0.79
    Act Density 0.000%

    No Known Activations