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

    Neuronpedia

    INDEX
    Explanations

    discussions about product comparisons and features

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

    as far as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.65
     houſe
    -0.62
     purpoſe
    -0.61
     deſt
    -0.57
     cauſe
    -0.57
     ſtate
    -0.57
     ſtre
    -0.57
    ſy
    -0.53
    ſelf
    -0.53
     Sensitive
    -0.52
    POSITIVE LOGITS
     Konkurrenz
    0.46
     createSlice
    0.40
     Überras
    0.37
    각주
    0.36
     Böh
    0.35
    Sucesor
    0.33
     Überg
    0.32
     Jakob
    0.32
    TargetException
    0.32
     ENGINEER
    0.32
    Act Density 0.049%

    No Known Activations