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

    Neuronpedia

    INDEX
    Explanations

    themes related to superiority and personal values

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

    abstract concepts and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bif
    -0.61
    RTGC
    -0.60
    abetes
    -0.59
    -0.59
    radan
    -0.59
    ufs
    -0.58
    SpringBootTest
    -0.57
    pire
    -0.57
    hila
    -0.56
    asiness
    -0.56
    POSITIVE LOGITS
    Personendaten
    0.39
     dragón
    0.33
    rungsseite
    0.33
    ThemeOverlay
    0.29
     thème
    0.29
    böz
    0.29
     الحره
    0.28
     culturales
    0.27
     mystère
    0.27
    ソッド
    0.26
    Act Density 0.026%

    No Known Activations