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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or structural elements in the text

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

    Characters introducing subsequent information

    np_acts-logits-general · gemini-2.0-flash

    region containing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.87
     also
    -0.86
     GenerationType
    -0.81
    adaptiveStyles
    -0.79
    دانشنامهٔ
    -0.77
     CascadeType
    -0.77
     linkovi
    -0.77
     moreover
    -0.76
    Aiheesta
    -0.74
    Collegamenti
    -0.74
    POSITIVE LOGITS
     Firstly
    0.95
    Firstly
    0.87
     firstly
    0.73
     The
    0.72
    <strong>
    0.71
     einerseits
    0.70
    <b>
    0.69
     First
    0.69
    　・
    0.69
    首先
    0.68
    Act Density 0.277%

    No Known Activations