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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or states related to success

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

    director or owner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.75
    LookAnd
    -0.75
    AddTagHelper
    -0.72
    principalColumn
    -0.71
    ValueStyle
    -0.70
    StructEnd
    -0.68
    WriteTagHelper
    -0.66
    delwed
    -0.63
    ngrx
    -0.62
     >=",
    -0.60
    POSITIVE LOGITS
     sahibi
    0.39
    ksessa
    0.29
     odası
    0.28
     takımı
    0.28
    asında
    0.28
    jenost
    0.28
     diretor
    0.27
     Parmi
    0.27
     director
    0.26
     yaşında
    0.26
    Act Density 0.432%

    No Known Activations