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

    Neuronpedia

    INDEX
    Explanations

    prepositions and phrases that describe locations and places

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

    in place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    izr
    -0.48
    EndInit
    -0.47
    
    -0.47
    AccessFile
    -0.46
    readAs
    -0.45
    PerformLayout
    -0.45
     beginnetje
    -0.45
     jspb
    -0.44
    corbic
    -0.44
    AnimationsModule
    -0.44
    POSITIVE LOGITS
     centered
    0.41
    HasAnnotation
    0.40
     없습니다
    0.39
    もちゃ
    0.36
    ソッド
    0.36
    0.36
     咖
    0.36
     centred
    0.35
    adam
    0.35
     يتيمه
    0.35
    Act Density 0.031%

    No Known Activations