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

    Neuronpedia

    INDEX
    Explanations

    affirmative answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    फत
    0.63
     solving
    0.61
     kendi
    0.58
    ക്കായി
    0.56
    াধি
    0.55
     sought
    0.55
    duire
    0.54
     গেল
    0.54
     sets
    0.54
    wakilan
    0.53
    POSITIVE LOGITS
     Yes
    5.35
     yes
    5.33
    Yes
    5.20
    yes
    4.80
     YES
    4.71
    YES
    4.40
     yeah
    3.61
     oui
    3.49
     Yeah
    3.44
     yep
    3.42
    Act Density 0.588%

    No Known Activations