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

    Neuronpedia

    INDEX
    Explanations

    instances of a single character or symbol that signify continuation or separation in contexts related to textual parsing

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

    after harassment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Πηγές
    -0.59
    ibouti
    -0.53
     CreateTagHelper
    -0.53
     NOI
    -0.52
    \{\\
    -0.52
    MigrationBuilder
    -0.51
     unwittingly
    -0.51
    -0.51
    initas
    -0.51
    printStackTrace
    -0.50
    POSITIVE LOGITS
     Италијани
    0.52
    rrggbb
    0.40
     الرياضيه
    0.38
    Datuak
    0.35
    0.32
    는데
    0.32
    graphique
    0.31
     menggambarkan
    0.30
    цездатний
    0.30
     يتيمه
    0.29
    Act Density 0.000%

    No Known Activations