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

    Neuronpedia

    INDEX
    Explanations

    specifies details and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    имость
    0.53
     faulty
    0.52
    wares
    0.50
    हट
    0.50
     стоимо
    0.49
     formalin
    0.49
    ។
    0.49
    ihilation
    0.48
     careless
    0.48
    rugated
    0.48
    POSITIVE LOGITS
    决定
    0.49
    带
    0.48
     parserOptions
    0.46
    西
    0.46
    ด
    0.45
    用
    0.44
    在
    0.44
    会
    0.44
    回答
    0.44
     Browning
    0.43
    Act Density 0.000%

    No Known Activations