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

    Neuronpedia

    INDEX
    Explanations

    email closings and sign-offs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rd
    0.63
    ద్
    0.62
    ү
    0.61
    iso
    0.61
    igr
    0.59
     ب
    0.59
    qc
    0.58
    ത
    0.58
     उठ
    0.57
    trx
    0.57
    POSITIVE LOGITS
     PS
    0.99
     Ps
    0.89
    PS
    0.88
    ▬▬
    0.86
     ps
    0.84
     PlayStation
    0.80
    ———
    0.79
     -----
    0.79
     Diary
    0.78
    ────────
    0.74
    Act Density 0.073%

    No Known Activations