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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to babies and baby-related items

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

    baby

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    -0.36
     "
    -0.29
     supporting
    -0.28
           
    -0.27
     ho
    -0.27
     primarily
    -0.27
     stop
    -0.27
    .
    -0.27
     $\
    -0.26
     //
    -0.26
    POSITIVE LOGITS
    baby
    1.23
    Baby
    1.23
     BABY
    1.21
     Baby
    1.21
    BABY
    1.20
     baby
    1.08
     Babies
    1.01
     bébé
    1.00
    babies
    0.96
    Babies
    0.96
    Act Density 0.012%

    No Known Activations