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

    Neuronpedia

    INDEX
    Explanations

    13th Amendment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    0.94
    ORES
    0.90
    り
    0.84
     thoại
    0.84
    سی
    0.75
     collusion
    0.75
    үр
    0.75
     Deport
    0.73
     метр
    0.73
     monolayers
    0.73
    POSITIVE LOGITS
     spoloč
    0.97
    hoe
    0.87
    iny
    0.87
    ure
    0.86
    տ
    0.84
    ic
    0.83
    ak
    0.83
    ik
    0.82
     jedną
    0.82
    ilene
    0.81
    Act Density 0.001%

    No Known Activations