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

    Neuronpedia

    INDEX
    Explanations

    page

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    物
    -0.07
    .department
    -0.07
    _reports
    -0.07
     Highway
    -0.07
     preset
    -0.07
    usiness
    -0.07
    izational
    -0.06
     kisses
    -0.06
    _employee
    -0.06
    /Error
    -0.06
    POSITIVE LOGITS
    Northern
    0.06
    (gulp
    0.06
    [$_
    0.06
     romant
    0.06
    콜걸
    0.06
    SPELL
    0.06
    .EXTRA
    0.06
     béné
    0.06
    сий
    0.06
     stál
    0.06
    Act Density 0.020%

    No Known Activations