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

    Neuronpedia

    INDEX
    Explanations

    references to user actions and experiences

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

    I'm going to need a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dragón
    -0.33
     dumne
    -0.30
     împre
    -0.30
     pasada
    -0.29
     león
    -0.29
     creș
    -0.28
    ************/
    -0.27
     aplicado
    -0.27
     recrutement
    -0.26
     táctil
    -0.26
    POSITIVE LOGITS
    MessageTagHelper
    0.77
    RTEX
    0.64
    SBATCH
    0.64
     ſei
    0.61
    frust
    0.60
    writeFieldEnd
    0.59
    RefNanny
    0.58
    Parcelize
    0.57
     Frust
    0.56
    binar
    0.55
    Act Density 0.018%

    No Known Activations