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

    Neuronpedia

    INDEX
    Explanations

    the presence of control signals or directives in the text

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

    Following certain numbers and symbols

    np_acts-logits-general · gemini-2.0-flash

    San Luis Obispo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Географи
    -0.49
    ()-
    -0.49
     complex
    -0.49
     devoirs
    -0.48
    تقاوى
    -0.48
    MigrationBuilder
    -0.47
    inigung
    -0.47
    ()];
    -0.46
     SqlCommand
    -0.45
    ()[
    -0.45
    POSITIVE LOGITS
     Majefty
    0.88
     themſelves
    0.87
     myſelf
    0.83
     itſelf
    0.79
     Efq
    0.77
     Jefus
    0.77
     himſelf
    0.77
     poffible
    0.76
     Houſe
    0.74
    ſelves
    0.74
    Act Density 0.080%

    No Known Activations