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

    Neuronpedia

    INDEX
    Explanations

    issues related to bias and misinterpretation in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    accuracy, errors, and results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chamber
    -0.38
     Kammer
    -0.37
    LookAnd
    -0.36
    稜
    -0.35
     Everyone
    -0.34
     Henne
    -0.33
     pil
    -0.33
    相信
    -0.33
    Welcome
    -0.33
     airplane
    -0.32
    POSITIVE LOGITS
    providedIn
    0.71
     eſſ
    0.59
    Personensuche
    0.56
     ſta
    0.55
     Eſ
    0.55
    mybatisplus
    0.54
     myſelf
    0.53
     canst
    0.50
     juſ
    0.50
     ſtand
    0.50
    Act Density 0.190%

    No Known Activations