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

    Neuronpedia

    INDEX
    Explanations

    first meeting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maze
    -0.07
     Все
    -0.07
    Scaled
    -0.07
     BP
    -0.07
     واحد
    -0.07
    ちょっと
    -0.06
    iles
    -0.06
    Elf
    -0.06
     algum
    -0.06
    ||||
    -0.06
    POSITIVE LOGITS
     освіт
    0.07
     zich
    0.06
    _Description
    0.06
     性
    0.06
    'name
    0.05
     uplat
    0.05
    ặp
    0.05
     resonate
    0.05
     SharedModule
    0.05
    τέ
    0.05
    Act Density 0.048%

    No Known Activations