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

    Neuronpedia

    INDEX
    Explanations

    chemical compound names and specific scientific terminology

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

    chemical compound names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.78
     cuantos
    -0.57
     fijo
    -0.56
     pouvoit
    -0.55
     חיצוניים
    -0.54
     feroit
    -0.54
     actuaciones
    -0.54
    Diweddarwch
    -0.53
     Relaciones
    -0.52
     mío
    -0.52
    POSITIVE LOGITS
    ]")
    0.53
    ]')
    0.47
    ()");
    0.47
    ]^{
    0.45
    "}")
    0.45
    ]-\
    0.44
    )$_
    0.44
    ))),
    0.44
     >",
    0.44
    ]<
    0.44
    Act Density 0.176%

    No Known Activations