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

    Neuronpedia

    INDEX
    Explanations

    extenuating circumstances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enjoy
    0.52
     ADJUST
    0.52
     unpack
    0.50
     belanja
    0.49
    📼
    0.48
     masukkan
    0.48
     tasso
    0.48
     vídeo
    0.47
     multichannel
    0.47
     inventory
    0.47
    POSITIVE LOGITS
    ia
    0.72
    ino
    0.64
    ene
    0.63
    ak
    0.63
    ola
    0.61
    uri
    0.59
    io
    0.59
    ip
    0.57
    ih
    0.57
    amino
    0.57
    Act Density 0.004%

    No Known Activations