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

    Neuronpedia

    INDEX
    Explanations

    conjunctions in a document

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

    linking geographical regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    éndole
    -0.43
     wuß
    -0.41
    kregen
    -0.39
     otorg
    -0.37
     ejecutivo
    -0.36
     lengkap
    -0.36
    tudiant
    -0.36
     soportes
    -0.36
     accesorio
    -0.35
     russes
    -0.35
    POSITIVE LOGITS
    StoryboardSegue
    0.63
     throughout
    0.62
    InitVars
    0.59
    Portale
    0.59
     Abroad
    0.57
     southern
    0.57
     Everywhere
    0.57
     across
    0.57
    throughout
    0.56
     Throughout
    0.55
    Act Density 0.102%

    No Known Activations