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

    Neuronpedia

    INDEX
    Explanations

    outer covering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Workshop
    0.73
    াফিক
    0.71
     Workshops
    0.69
    Fit
    0.69
    Steady
    0.65
    Signal
    0.64
     Signal
    0.64
    signal
    0.62
    Cast
    0.61
    cast
    0.61
    POSITIVE LOGITS
     sheets
    1.00
     roof
    0.96
     petals
    0.94
     lids
    0.92
     roofs
    0.87
     sails
    0.83
     curtains
    0.83
     banknotes
    0.83
     lid
    0.82
     papers
    0.80
    Act Density 0.440%

    No Known Activations