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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal concepts and courtroom dynamics

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

    mocked, attack, defense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setLayoutManager
    -0.35
    Prote
    -0.33
    vency
    -0.31
     reputación
    -0.31
     protectors
    -0.31
     entretien
    -0.30
     proteger
    -0.30
     protecting
    -0.29
     okru
    -0.29
    prote
    -0.28
    POSITIVE LOGITS
    MockMvc
    0.67
     ExecuteAsync
    0.63
    #+#
    0.62
     noDo
    0.60
    +#+
    0.59
     kasarigan
    0.56
    (!__
    0.56
    RTGC
    0.54
    setof
    0.54
     mocking
    0.52
    Act Density 0.090%

    No Known Activations