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

    Neuronpedia

    INDEX
    Explanations

    introduces specific concepts or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stvari
    0.47
    섦
    0.46
     იყოს
    0.45
     Also
    0.43
     poisons
    0.42
     سوال
    0.41
     wares
    0.41
     cosas
    0.41
     Sunt
    0.41
     برای
    0.41
    POSITIVE LOGITS
     elegant
    0.62
     impressive
    0.58
     innovative
    0.57
     unassuming
    0.57
     renowned
    0.56
     acclaimed
    0.55
     highly
    0.55
     groundbreaking
    0.54
     prestigious
    0.53
     stunning
    0.52
    Act Density 0.055%

    No Known Activations