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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases that denote mathematical or scientific expressions and their context

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

    in followed by the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.58
    Попис
    -0.54
     gynhyrchwyd
    -0.53
    UnusedPrivate
    -0.53
     oprot
    -0.51
     الرياضيه
    -0.50
     rospy
    -0.50
    Datuak
    -0.49
    tvguidetime
    -0.49
    copyWith
    -0.48
    POSITIVE LOGITS
     makeStyles
    0.36
    称为
    0.35
    这就是
    0.34
    可谓
    0.33
     LEYENDO
    0.32
     cherchés
    0.31
    這就是
    0.31
    那种
    0.30
     korun
    0.30
     वाली
    0.30
    Act Density 0.856%

    No Known Activations