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

    Neuronpedia

    INDEX
    Explanations

    late/former followed by people/roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    أ
    0.93
    כ
    0.85
    на
    0.82
    ان
    0.82
    g
    0.81
    šću
    0.81
    ine
    0.80
    Accueil
    0.78
    מ
    0.78
    ANCE
    0.75
    POSITIVE LOGITS
    𝗸
    0.77
    𝘀
    0.73
     Teresa
    0.72
     skyrocketing
    0.71
    लिब्र
    0.71
    𝘇
    0.70
     incarcer
    0.69
    𝘆
    0.69
     Pulitzer
    0.69
     Eminem
    0.69
    Act Density 0.000%

    No Known Activations