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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Manager
    -0.07
    化的
    -0.07
    Problem
    -0.07
    ListView
    -0.07
    Chuck
    -0.07
     efter
    -0.07
    出台
    -0.07
     интер
    -0.07
     cười
    -0.07
     Director
    -0.06
    POSITIVE LOGITS
    _digest
    0.07
    xdd
    0.07
    风景
    0.07
    初步
    0.06
    (lhs
    0.06
    .remote
    0.06
     hobbies
    0.06
    �
    0.06
    Digest
    0.06
     getter
    0.06
    Act Density 0.164%

    No Known Activations