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

    Neuronpedia

    INDEX
    Explanations

    does not constitute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     likeness
    0.81
    \|$.
    0.77
    $.\
    0.73
     remarked
    0.69
     Trademark
    0.68
     drama
    0.67
     Saltar
    0.66
     damaging
    0.65
     Fortunately
    0.65
     halted
    0.65
    POSITIVE LOGITS
    aksud
    0.87
    Martin
    0.84
    ifika
    0.82
    创建一个
    0.80
    create
    0.77
    Созда
    0.76
    kuat
    0.76
    Formation
    0.76
    Globalization
    0.75
    Creating
    0.75
    Act Density 0.001%

    No Known Activations