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

    Neuronpedia

    INDEX
    Explanations

    instances of failure or non-compliance in various contexts

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

    negative outcomes or realizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.53
    Enllaços
    -0.49
     незавершена
    -0.44
     CreateTagHelper
    -0.41
    日閲覧
    -0.41
    Bism
    -0.40
    wach
    -0.39
    StoryboardSegue
    -0.38
    HasForeignKey
    -0.37
    /$',
    -0.37
    POSITIVE LOGITS
    thâu
    0.49
    Jeografia
    0.47
    Togo
    0.45
    DockStyle
    0.44
    addContainerGap
    0.41
    PropertyChanging
    0.41
     ligiloj
    0.40
     surla
    0.39
    pgterms
    0.39
    stdc
    0.39
    Act Density 0.093%

    No Known Activations