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

    Neuronpedia

    INDEX
    Explanations

    words related to designing and creating things

    oai_token-act-pair · gemini-2.0-flash

    designing and creating

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.85
    UnusedPrivate
    -0.81
    
    -0.75
    VersionUID
    -0.63
     betweenstory
    -0.63
    RegistryLite
    -0.60
    Hochspringen
    -0.59
    WithIOException
    -0.57
     مشارکت‌کنندگان
    -0.57
     estekak
    -0.56
    POSITIVE LOGITS
    xnn
    0.54
     calendriers
    0.53
     cho
    0.49
    ာ
    0.48
     simple
    0.48
     acuerdo
    0.47
    δο
    0.45
    rops
    0.45
     BL
    0.44
     [
    0.44
    Act Density 7.732%

    No Known Activations