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

    Neuronpedia

    INDEX
    Explanations

    Java code that initializes JLabels

    oai_token-act-pair · gemini-2.0-flash

    Code labels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     animés
    -0.55
    kranz
    -0.55
     communs
    -0.54
     internationaux
    -0.52
     étrangers
    -0.52
     decisione
    -0.48
     extérieurs
    -0.47
     Boyd
    -0.47
     nationaux
    -0.47
     aguacate
    -0.47
    POSITIVE LOGITS
    ArrowToggle
    1.00
    setVerticalGroup
    0.87
    <bos>
    0.79
     CreateTagHelper
    0.77
    Hentet
    0.74
    kháu
    0.71
    andExpect
    0.71
    TintMode
    0.71
    enumi
    0.70
     nakalista
    0.69
    Act Density 0.519%

    No Known Activations