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

    Neuronpedia

    INDEX
    Explanations

    topics related to permissions and documentation in various contexts

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

    followed by "about"

    np_acts-logits-general · gemini-2.0-flash

    issues and their consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ädie
    -0.51
    interopRequire
    -0.51
    iseks
    -0.49
     serez
    -0.48
    kheim
    -0.45
    所に
    -0.45
     fizer
    -0.44
    kens
    -0.43
    ➟
    -0.43
     ProtoMessage
    -0.43
    POSITIVE LOGITS
    ThroughAttribute
    0.86
     ועל
    0.81
     matters
    0.78
    ')['
    0.71
    是如何
    0.70
     topics
    0.67
    XmlAccessType
    0.67
     esternos
    0.66
     ogóle
    0.65
     topic
    0.65
    Act Density 0.618%

    No Known Activations