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

    Neuronpedia

    INDEX
    Explanations

    To Kill, To Sell, Toilets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    맞
    0.41
     Cep
    0.39
     incid
    0.37
     esfera
    0.37
    判定
    0.37
     priprav
    0.37
     memnun
    0.37
    mén
    0.36
    恝
    0.35
     sahip
    0.35
    POSITIVE LOGITS
    ffee
    0.66
    ppling
    0.62
    pping
    0.57
    ppings
    0.57
    pper
    0.54
    asty
    0.52
    ppled
    0.52
    pple
    0.51
    asting
    0.51
    ilets
    0.50
    Act Density 0.007%

    No Known Activations