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

    Neuronpedia

    INDEX
    Explanations

    wiki/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biodegrad
    0.74
     mini
    0.69
     mileage
    0.66
     misalignment
    0.66
     campaigns
    0.63
     gang
    0.63
     attenuation
    0.63
     ministers
    0.62
     solicita
    0.62
     lab
    0.61
    POSITIVE LOGITS
    .).
    0.77
    Woman
    0.74
    spaces
    0.73
    Spaces
    0.72
     Voting
    0.72
    Voting
    0.69
    Women
    0.68
    $)$.
    0.68
     Woman
    0.67
    .)
    0.67
    Act Density 0.005%

    No Known Activations