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

    Neuronpedia

    INDEX
    Explanations

    road prefixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Acts
    -0.07
     nargs
    -0.07
    IntArray
    -0.07
     ин
    -0.07
     entities
    -0.06
     §§
    -0.06
     věn
    -0.06
    >Nama
    -0.06
    -tax
    -0.06
    zones
    -0.06
    POSITIVE LOGITS
     condition
    0.06
    .onDestroy
    0.06
    láš
    0.06
     dug
    0.06
    _INITIALIZ
    0.06
    �
    0.06
    FFF
    0.06
    vk
    0.06
    电影
    0.05
    -shadow
    0.05
    Act Density 0.008%

    No Known Activations