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

    Neuronpedia

    INDEX
    Explanations

    cash advance services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    0.90
    eby
    0.87
    reaching
    0.86
    ष्ठी
    0.85
    اء
    0.85
    appi
    0.85
    or
    0.84
    enth
    0.83
    tiered
    0.83
    pid
    0.83
    POSITIVE LOGITS
     old
    0.92
     đây
    0.90
     mañana
    0.89
     ancien
    0.89
     flops
    0.89
     shit
    0.88
     groceries
    0.87
     голо
    0.86
     Else
    0.85
     mẹ
    0.85
    Act Density 0.001%

    No Known Activations