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

    Neuronpedia

    INDEX
    Explanations

    Data analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    manız
    -0.06
     inhibition
    -0.06
    (tol
    -0.06
    _news
    -0.06
    ện
    -0.06
     CASCADE
    -0.06
     zásad
    -0.06
    위
    -0.06
    maries
    -0.06
    982
    -0.06
    POSITIVE LOGITS
     hang
    0.06
     MUT
    0.06
    IEEE
    0.06
     draw
    0.06
     plag
    0.06
    IGHT
    0.06
    蒂
    0.06
     작
    0.06
    usto
    0.06
    �
    0.06
    Act Density 0.003%

    No Known Activations