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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with lists or selections

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

    Code snippets or strings

    np_acts-logits-general · gemini-2.0-flash

    numbers and short words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.93
     estekak
    -0.75
     EconPapers
    -0.73
    ArgsConstructor
    -0.70
    AccessorTable
    -0.70
    ViewFeatures
    -0.69
     enfans
    -0.67
    DockStyle
    -0.65
     NgModule
    -0.64
    seamnă
    -0.63
    POSITIVE LOGITS
       
    0.71
         
    0.63
     str
    0.62
           
    0.55
          
    0.55
        
    0.55
     String
    0.50
    if
    0.50
             
    0.50
     ​
    0.49
    Act Density 0.063%

    No Known Activations