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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     caste
    -0.07
    avra
    -0.06
    陆
    -0.06
     scalar
    -0.06
     TREE
    -0.06
    转
    -0.05
    _aa
    -0.05
     swelling
    -0.05
     undermines
    -0.05
     xor
    -0.05
    POSITIVE LOGITS
     ऑनल
    0.07
    увала
    0.07
     Hedge
    0.07
     Dys
    0.07
    .Offset
    0.07
    _actor
    0.07
     rake
    0.07
     правил
    0.06
     hudeb
    0.06
    リスト
    0.06
    Act Density 0.133%

    No Known Activations