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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing equality or balance

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

    equally followed by various descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ആ
    -0.35
    Org
    -0.35
    DOB
    -0.35
    name
    -0.35
     ГО
    -0.34
     Control
    -0.34
     doanh
    -0.34
     Removal
    -0.33
     slik
    -0.33
     Stabilization
    -0.33
    POSITIVE LOGITS
     equally
    1.05
     Equally
    0.89
     Ebenso
    0.76
     igualmente
    0.74
    Personensuche
    0.71
     betweenstory
    0.70
     wikipagina
    0.69
    UTELY
    0.69
     Италијани
    0.69
    zelfde
    0.69
    Act Density 0.010%

    No Known Activations