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

    Neuronpedia

    INDEX
    Explanations

    JSON object structures and their properties

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

    Characters commonly found in JSON or code

    np_acts-logits-general · gemini-2.0-flash

    Spanish, figure, except

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    luk
    -0.56
     off
    -0.53
    ;}
    -0.51
    ži
    -0.50
    late
    -0.50
     def
    -0.49
     ठ
    -0.49
    τώ
    -0.48
    ())))
    -0.48
    rogen
    -0.47
    POSITIVE LOGITS
    msgTypes
    0.73
     يتيمه
    0.70
     فريبيس
    0.70
     jScrollPane
    0.70
    BufferException
    0.69
     CreateTagHelper
    0.69
    Bakgrunnsstoff
    0.67
     contextLoads
    0.66
     pinulongan
    0.65
    ſelves
    0.64
    Act Density 0.059%

    No Known Activations