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

    Neuronpedia

    INDEX
    Explanations

    exploitative content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    으로
    0.51
    räume
    0.50
    ность
    0.47
    রকম
    0.46
    ᱚ
    0.46
    ᱤ
    0.46
    seiten
    0.45
    ोच्च
    0.44
    ਾਂ
    0.44
    ্রো
    0.44
    POSITIVE LOGITS
    pper
    1.26
    pping
    1.23
    pped
    1.20
    ppers
    1.13
    ppy
    1.05
    pp
    1.00
    fficial
    0.98
    ppen
    0.96
    ğlu
    0.92
    ppa
    0.91
    Act Density 0.086%

    No Known Activations