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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or criticisms in various contexts

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

    numbers followed by units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Życiorys
    -0.45
    hoeddwyd
    -0.45
     Meksiku
    -0.42
     idag
    -0.40
    قایناقلار
    -0.39
    richTextPanel
    -0.39
     låg
    -0.38
     Numerade
    -0.35
     vérit
    -0.35
    AlterField
    -0.35
    POSITIVE LOGITS
    Clik
    0.56
    bsch
    0.55
    scher
    0.53
    hode
    0.53
    ologous
    0.52
    fml
    0.52
    llum
    0.52
    bory
    0.52
    hogy
    0.51
     invokingState
    0.51
    Act Density 0.068%

    No Known Activations