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

    Neuronpedia

    INDEX
    Explanations

    post for, postgreSQL, post confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    1.50
    2
    1.37
    다
    1.16
    า
    1.15
    ה
    1.01
    ير
    0.98
    ين
    0.96
    я
    0.93
    ا
    0.93
    ان
    0.91
    POSITIVE LOGITS
     for
    1.13
    n
    0.98
     mortem
    0.88
     nouvel
    0.86
     post
    0.85
    t
    0.85
    G
    0.84
    mortem
    0.83
     escult
    0.80
    ク
    0.80
    Act Density 0.033%

    No Known Activations