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

    Neuronpedia

    INDEX
    Explanations

    patterns associated with functional code structures and execution conditions

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

    Code or configuration snippets

    np_acts-logits-general · gemini-2.0-flash

    code initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.98
    MessageOf
    -0.74
    ſelf
    -0.72
    omiast
    -0.66
     وتسجيلات
    -0.66
     Theſe
    -0.66
    IonicModule
    -0.66
     pleaſure
    -0.65
     raiſ
    -0.65
     purpoſe
    -0.65
    POSITIVE LOGITS
            
    0.68
    kapnya
    0.45
    carril
    0.45
     Mota
    0.44
    گرام
    0.43
          
    0.43
    OutOfRange
    0.41
    fractal
    0.40
    sertation
    0.40
    jabi
    0.39
    Act Density 0.039%

    No Known Activations