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

    Neuronpedia

    INDEX
    Explanations

    people who care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mottled
    0.80
    <unused578>
    0.77
     thumbnails
    0.76
    <unused367>
    0.76
    ZZ
    0.75
     halv
    0.75
     smelled
    0.74
     stunned
    0.74
     darkened
    0.73
    <unused352>
    0.73
    POSITIVE LOGITS
     care
    0.84
     Care
    0.76
    ケア
    0.71
     CARE
    0.70
    CARE
    0.70
     cares
    0.67
    care
    0.64
    ществует
    0.60
     सकेगा
    0.60
    がございます
    0.60
    Act Density 0.009%

    No Known Activations