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

    Neuronpedia

    INDEX
    Explanations

    forget

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    人才
    -0.08
    _network
    -0.07
     reverse
    -0.07
     会
    -0.06
     polym
    -0.06
     database
    -0.06
     输入
    -0.06
     library
    -0.06
     zur
    -0.06
    อ
    -0.06
    POSITIVE LOGITS
    تیجه
    0.07
    ्त
    0.07
    ok
    0.06
    ा↵↵
    0.06
    _less
    0.06
    Ÿ
    0.06
    _requirements
    0.06
    ันธ
    0.06
     розповід
    0.06
    Thinking
    0.06
    Act Density 0.004%

    No Known Activations