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

    Neuronpedia

    INDEX
    Explanations

    to isolate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    არგ
    0.44
    过滤器
    0.43
    睒
    0.41
    زام
    0.40
     ምስ
    0.40
    格子
    0.40
    剌
    0.39
     короля
    0.39
    Tokens
    0.39
    ագր
    0.39
    POSITIVE LOGITS
     efficiency
    0.44
     characteristic
    0.42
     discuss
    0.42
     autonomous
    0.42
     Efficiency
    0.40
     unrest
    0.39
     dwelling
    0.39
     lecture
    0.39
     patient
    0.38
     HIR
    0.38
    Act Density 0.000%

    No Known Activations