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

    Neuronpedia

    INDEX
    Explanations

    terms of endearment

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to affectionate pet names—particularly the word “sweetie.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ωμά
    -0.06
     Iterator
    -0.06
    Where
    -0.06
    mploy
    -0.06
     hafif
    -0.06
     ماد
    -0.06
     Ihre
    -0.06
     PRODUCT
    -0.06
    NotNil
    -0.06
     Living
    -0.05
    POSITIVE LOGITS
     party
    0.07
    types
    0.07
     aggress
    0.07
    edef
    0.07
    .tipo
    0.07
     garn
    0.07
    �
    0.06
    serialize
    0.06
    -party
    0.06
     institutes
    0.06
    Act Density 0.030%

    No Known Activations