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

    Neuronpedia

    INDEX
    Explanations

    self-criticism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ANTA
    -0.07
     управления
    -0.07
    지가
    -0.07
     Lambda
    -0.06
    아이
    -0.06
    _CI
    -0.06
     타
    -0.06
    하지
    -0.06
     supervised
    -0.06
     стоит
    -0.06
    POSITIVE LOGITS
     dall
    0.06
    ":""
    0.06
     danced
    0.06
    译
    0.06
    افه
    0.06
    .LabelControl
    0.06
     "-",
    0.06
     :";↵
    0.06
     Demp
    0.06
    .Role
    0.06
    Act Density 0.061%

    No Known Activations