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

    Neuronpedia

    INDEX
    Explanations

    negations related to necessity or similarity

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

    not necessarily, not only, not without

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.62
    fromnode
    -0.51
    rungsseite
    -0.46
    sidemargin
    -0.45
    ValueStyle
    -0.45
    الدراسه
    -0.45
    styleType
    -0.44
    SBATCH
    -0.44
    Hozzáférés
    -0.41
    ThroughAttribute
    -0.41
    POSITIVE LOGITS
     synonymous
    0.64
     itself
    0.60
     itſelf
    0.54
     unique
    0.52
    万能
    0.49
     exclusive
    0.48
     synonym
    0.48
     new
    0.47
     unusual
    0.47
     enough
    0.47
    Act Density 0.083%

    No Known Activations