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

    Neuronpedia

    INDEX
    Explanations

    proposals or potential resolutions to problems

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

    start of user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.47
     Decke
    -0.47
     kirja
    -0.43
     otomatig
    -0.42
    LabelTagHelper
    -0.42
     &___
    -0.41
     Ahnung
    -0.41
     Glaube
    -0.40
    queles
    -0.40
     limpio
    -0.38
    POSITIVE LOGITS
     DTS
    0.53
     TPS
    0.52
     betweenstory
    0.51
    нгред
    0.49
     SRS
    0.49
     continental
    0.49
     combi
    0.49
     SDN
    0.48
     classi
    0.47
     ostavi
    0.47
    Act Density 0.000%

    No Known Activations