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

    Neuronpedia

    INDEX
    Explanations

    looking for information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಲ
    1.35
     promised
    1.30
    ی
    1.26
    promised
    1.25
    ি
    1.25
    dismiss
    1.20
     கூடிய
    1.19
    a
    1.19
    lander
    1.19
    i
    1.17
    POSITIVE LOGITS
     retr
    1.00
    ជាមួយនឹង
    0.98
     Під
    0.98
    टोन
    0.97
    osite
    0.97
     pooch
    0.96
    Гор
    0.96
    କ୍
    0.95
     জ্ঞ
    0.95
     Й
    0.94
    Act Density 0.000%

    No Known Activations