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

    Neuronpedia

    INDEX
    Explanations

    website search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ക്കിയത്
    0.44
     anarchy
    0.44
     fleas
    0.41
     disagreeable
    0.40
     reminding
    0.40
    ુદ્ધ
    0.39
     negligent
    0.39
     killings
    0.39
     withd
    0.39
    ItemBackground
    0.39
    POSITIVE LOGITS
     View
    0.88
    View
    0.82
    <h4>
    0.81
    0
    0.78
    更多
    0.75
     BEST
    0.74
     Show
    0.73
    <h3>
    0.73
    See
    0.71
     Similar
    0.70
    Act Density 0.000%

    No Known Activations