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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    يلة
    -0.07
    (const
    -0.07
     todd
    -0.07
     Cục
    -0.06
     {}↵
    -0.06
     조교
    -0.06
     Retrie
    -0.06
    Directed
    -0.06
    对象
    -0.06
    (!$
    -0.06
    POSITIVE LOGITS
    орм
    0.07
    PASS
    0.06
    國
    0.06
     valido
    0.06
     произош
    0.06
    dem
    0.06
    mant
    0.06
    Stat
    0.06
     Aluminium
    0.06
    _sin
    0.06
    Act Density 2.023%

    No Known Activations