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

    Neuronpedia

    INDEX
    Explanations

    Basket

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     [=
    -0.07
    _ls
    -0.07
    jabi
    -0.07
    clus
    -0.06
    ,nonatomic
    -0.06
     �
    -0.06
    .bn
    -0.06
    씩
    -0.06
    uve
    -0.06
     Benedict
    -0.06
    POSITIVE LOGITS
     вещества
    0.07
     testimonials
    0.07
     extracts
    0.07
    Civil
    0.07
    uania
    0.06
     alter
    0.06
     доступ
    0.06
    .template
    0.06
    soon
    0.06
     Sampling
    0.06
    Act Density 0.115%

    No Known Activations