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

    Neuronpedia

    INDEX
    Explanations

    Manner of speaking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Attached
    -0.08
    (download
    -0.07
    @Module
    -0.07
     pst
    -0.07
     yr
    -0.07
     LX
    -0.07
    endl
    -0.06
     Buddh
    -0.06
     جلسه
    -0.06
     Interpret
    -0.06
    POSITIVE LOGITS
     Kurt
    0.06
    973
    0.06
     invoices
    0.06
    916
    0.06
    leftright
    0.06
    ฝ
    0.06
    _coeff
    0.06
     drop
    0.06
     arisen
    0.05
     currents
    0.05
    Act Density 0.047%

    No Known Activations