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

    Neuronpedia

    INDEX
    Explanations

    declare war, ban, close, approve, raise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desiderio
    0.69
     consultez
    0.68
     rarement
    0.67
     selezione
    0.67
     vaak
    0.66
     drowsiness
    0.66
     meestal
    0.65
    ప్రత్యర్థి
    0.65
    饮食
    0.64
     biasanya
    0.64
    POSITIVE LOGITS
     engineer
    0.75
     formally
    0.67
     belated
    0.66
     dramatically
    0.65
     unilaterally
    0.65
     औपचारिक
    0.63
     abruptly
    0.63
     ultimately
    0.62
     bowed
    0.62
     reversed
    0.61
    Act Density 0.049%

    No Known Activations