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

    Neuronpedia

    INDEX
    Explanations

    needed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Required
    -0.69
     necessary
    -0.67
     Necessary
    -0.65
     required
    -0.61
    necessary
    -0.61
    Required
    -0.58
    required
    -0.57
    Necessary
    -0.51
    خ
    -0.49
     needed
    -0.49
    POSITIVE LOGITS
     pleaſure
    0.78
     TAMBIÉN
    0.69
    phrine
    0.69
    setVerticalGroup
    0.68
     myſelf
    0.66
    StoryboardSegue
    0.66
    moiselle
    0.64
    theoremstyle
    0.63
    〼
    0.63
    +#+#
    0.62
    Act Density 0.052%

    No Known Activations