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

    Neuronpedia

    INDEX
    Explanations

    definitions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    会有
    0.40
     dovrà
    0.40
     ciddi
    0.39
    ()},
    0.39
     respectivas
    0.38
     Será
    0.37
    éticos
    0.36
    凭借
    0.36
    Conclusions
    0.35
    strij
    0.35
    POSITIVE LOGITS
     Definition
    0.87
    什么是
    0.84
     Essentially
    0.82
    Essentially
    0.82
     Basically
    0.80
     basically
    0.80
    Definition
    0.80
    Basically
    0.77
    basically
    0.77
     essentially
    0.72
    Act Density 0.086%

    No Known Activations