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

    Neuronpedia

    INDEX
    Explanations

    technical terms and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itabbo
    0.49
    रत
    0.48
     Indo
    0.44
    は大
    0.43
    ishima
    0.43
    łem
    0.43
     condemnation
    0.42
     corpi
    0.42
     грамо
    0.42
     กับ
    0.41
    POSITIVE LOGITS
    chloro
    0.44
    িখিত
    0.44
     yar
    0.44
    scrire
    0.43
     derfor
    0.43
     Reactor
    0.42
    Bird
    0.42
     Branch
    0.42
     cabelo
    0.41
    大气
    0.41
    Act Density 0.001%

    No Known Activations