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

    Neuronpedia

    INDEX
    Explanations

    man or woman subject

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Their
    0.86
     Hogwarts
    0.86
     their
    0.80
     neuer
    0.79
     choc
    0.78
     Personnel
    0.77
     Neues
    0.77
     some
    0.73
     Vegeta
    0.73
     The
    0.73
    POSITIVE LOGITS
    కు
    0.94
    hattam
    0.86
    𝓁
    0.86
    alık
    0.84
    rı
    0.83
    ﻜ
    0.83
    ﺤ
    0.83
    œuvre
    0.82
    л
    0.82
    σκεται
    0.81
    Act Density 0.011%

    No Known Activations