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

    Neuronpedia

    INDEX
    Explanations

    instances of HTML tags or code snippets

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

    structured input tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.76
     Infórmanos
    -0.68
     الرياضيه
    -0.66
    ngrx
    -0.65
    RetentionPolicy
    -0.63
     OFDb
    -0.60
     defaultstate
    -0.59
     مرئيه
    -0.58
    AndEndTag
    -0.57
    AxisAlignment
    -0.57
    POSITIVE LOGITS
    
    0.59
    
    0.45
     bulu
    0.35
    
    0.35
    expandindo
    0.35
    
    0.32
     Heidelberg
    0.30
    lik
    0.29
    견
    0.29
    <0x00>
    0.29
    Act Density 0.000%

    No Known Activations