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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    barang
    -0.07
    oron
    -0.06
    _vertical
    -0.06
     gerekli
    -0.06
    　　　　　
    -0.06
     Ms
    -0.06
    <|python_tag|>
    -0.06
    <k
    -0.06
    での
    -0.06
    Suite
    -0.06
    POSITIVE LOGITS
     reluctant
    0.07
     feet
    0.07
    .Orders
    0.07
     reluctance
    0.07
     incompetent
    0.07
     CGContext
    0.07
     EMP
    0.06
    .segments
    0.06
    무
    0.06
     abusive
    0.06
    Act Density 0.011%

    No Known Activations