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

    Neuronpedia

    INDEX
    Explanations

    strict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sahiptir
    -0.07
    belie
    -0.07
     yoktur
    -0.07
     astronom
    -0.07
    -net
    -0.06
    ButtonText
    -0.06
    结
    -0.06
     inconvenient
    -0.06
    ❤
    -0.06
     kendisini
    -0.06
    POSITIVE LOGITS
    ète
    0.06
     sexes
    0.06
    verages
    0.06
     Continued
    0.06
     RecyclerView
    0.06
     pimp
    0.06
     Camel
    0.06
     traditional
    0.06
    ISHED
    0.06
     marc
    0.06
    Act Density 0.000%

    No Known Activations