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

    Neuronpedia

    INDEX
    Explanations

    specific concepts and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     في
    0.51
    v
    0.48
     definitively
    0.47
     in
    0.46
    agens
    0.43
    在
    0.43
     be
    0.41
    stig
    0.40
     the
    0.39
    quality
    0.39
    POSITIVE LOGITS
     Tuttavia
    0.50
     HOWEVER
    0.49
    frameN
    0.48
    ллер
    0.47
     nField
    0.47
    ಎಸ್
    0.47
     tokamak
    0.46
     radionuclides
    0.46
     şirk
    0.46
     تاہم
    0.46
    Act Density 0.003%

    No Known Activations