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

    Neuronpedia

    INDEX
    Explanations

    escalation, apology, lemon zest, risk level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Using
    0.41
     Businesses
    0.40
    使用
    0.39
     Creating
    0.39
     developed
    0.39
     erstellen
    0.39
     Software
    0.38
     Toronto
    0.38
     Financial
    0.38
    使用了
    0.38
    POSITIVE LOGITS
    addam
    0.46
     defies
    0.46
     defy
    0.45
     rumour
    0.45
     леген
    0.45
     fluctu
    0.44
    legend
    0.43
     rumor
    0.42
    ños
    0.42
     incertid
    0.41
    Act Density 0.001%

    No Known Activations