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

    Neuronpedia

    INDEX
    Explanations

    jailbreaking, rooting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /),
    0.63
    _),
    0.62
     Đường
    0.61
     અને
    0.61
     και
    0.58
    )],
    0.57
    埆
    0.57
     thiab
    0.55
    ải
    0.55
     xóa
    0.55
    POSITIVE LOGITS
     countenance
    0.56
     serv
    0.52
     determinations
    0.52
     analyzers
    0.51
     tiredness
    0.50
     headache
    0.49
     moul
    0.49
     bowels
    0.48
    alat
    0.48
    fdPar
    0.48
    Act Density 0.007%

    No Known Activations