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

    Neuronpedia

    INDEX
    Explanations

    explaining concepts and understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мето
    0.41
     egyéb
    0.40
     这里
    0.39
    这个时候
    0.39
    वाहक
    0.39
     Strategy
    0.39
     план
    0.38
     имя
    0.38
     titles
    0.38
     kurie
    0.38
    POSITIVE LOGITS
    esist
    0.39
    atro
    0.37
    didReceive
    0.36
    iy
    0.36
    แด
    0.36
    ode
    0.35
    athed
    0.34
     vig
    0.34
    esgue
    0.34
    inee
    0.34
    Act Density 0.000%

    No Known Activations