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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate assessment or evaluation of a situation or subject

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

    Considering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PopupWindow
    -0.42
     acts
    -0.39
    WithIOException
    -0.37
    createStatement
    -0.37
    ณ์
    -0.33
    FieldError
    -0.32
    Pathway
    -0.32
     reto
    -0.32
    tiges
    -0.31
    })->
    -0.31
    POSITIVE LOGITS
    发表于
    0.56
    indest
    0.54
    styleType
    0.52
     CreateTagHelper
    0.50
    ंदीखरीदारी
    0.50
    これだけ
    0.50
     vermelhas
    0.50
     שוליים
    0.49
    Похо
    0.47
    Impressive
    0.47
    Act Density 0.031%

    No Known Activations