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

    Neuronpedia

    INDEX
    Explanations

    references to requests, threats, allegations, and challenges in legal or confrontational contexts

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

    actions, allegations, or resistance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ynchronously
    -0.61
    OGND
    -0.60
    RegressionTest
    -0.59
     CreateTagHelper
    -0.54
    UnusedPrivate
    -0.53
    səhifə
    -0.53
     createSlice
    -0.48
     محفوظة
    -0.46
    ]")]
    -0.46
    gtest
    -0.45
    POSITIVE LOGITS
    Aholisi
    0.35
     otomatig
    0.34
    Източници
    0.34
    WireFormatLite
    0.31
    MessageTagHelper
    0.31
     terapé
    0.30
     onOptions
    0.30
     espalda
    0.29
    Skocz
    0.29
     propuestas
    0.29
    Act Density 0.237%

    No Known Activations