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

    Neuronpedia

    INDEX
    Explanations

    laughter and antidepressants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pr
    -0.54
     ar
    -0.54
     some
    -0.47
    omy
    -0.46
     en
    -0.46
     para
    -0.46
     dan
    -0.46
    <eos>
    -0.45
     strategies
    -0.44
    ardia
    -0.44
    POSITIVE LOGITS
     Theſe
    1.13
     Monfieur
    1.00
     Efq
    0.99
     Houſe
    0.94
     ―――――
    0.93
    ⓧ
    0.93
     houſe
    0.92
     myſelf
    0.91
     Beſ
    0.91
     itſelf
    0.89
    Act Density 1.602%

    No Known Activations