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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to scientific protocols and experimental designs

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

    concepts joined by and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Geiſt
    -0.82
     geſch
    -0.79
     verſch
    -0.74
     laſſen
    -0.73
    ſchaft
    -0.71
     vooz
    -0.69
     beſch
    -0.68
     wiſſen
    -0.68
     müſſen
    -0.67
     Waſſer
    -0.67
    POSITIVE LOGITS
     and
    2.45
    性和
    1.10
    และ
    1.09
    力和
    1.00
     и
    0.99
    そして
    0.98
    子和
    0.97
     và
    0.95
     और
    0.95
     &
    0.92
    Act Density 15.129%

    No Known Activations