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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rollers
    -0.06
    шов
    -0.06
    _RECV
    -0.06
    냐
    -0.06
     choir
    -0.06
     segunda
    -0.06
     文
    -0.06
     sung
    -0.06
     evet
    -0.06
    уру
    -0.06
    POSITIVE LOGITS
     Routing
    0.07
     catalog
    0.06
     Strength
    0.06
    _ROWS
    0.06
     https
    0.06
    _length
    0.06
     manipulating
    0.06
     Catalog
    0.06
    _attack
    0.06
    ?↵
    0.06
    Act Density 0.001%

    No Known Activations