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

    Neuronpedia

    INDEX
    Explanations

    spitting straight facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🥰
    0.49
     🥰
    0.47
     omg
    0.47
     OMG
    0.45
    ぅ
    0.45
     💕
    0.44
    OMG
    0.42
     💞
    0.42
    🥲
    0.42
     plz
    0.42
    POSITIVE LOGITS
     fire
    0.62
    fire
    0.61
     facts
    0.60
     Facts
    0.59
    straight
    0.58
     straight
    0.55
    facts
    0.55
     banged
    0.54
    火
    0.54
     Straight
    0.52
    Act Density 0.014%

    No Known Activations