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

    Neuronpedia

    INDEX
    Explanations

    Models induced by chemicals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     നേ
    -0.08
    anelas
    -0.07
    കാശ
    -0.07
    ables
    -0.07
     മുത
    -0.07
    പ്ര
    -0.07
    ന്ന
    -0.07
    ornost
    -0.07
     പക്ഷ
    -0.07
     хозяй
    -0.07
    POSITIVE LOGITS
     induced
    0.11
     model
    0.10
    模型
    0.10
     Modelo
    0.10
     Model
    0.10
     infection
    0.10
     modelo
    0.10
     challenge
    0.10
     модель
    0.09
     models
    0.09
    Act Density 0.005%

    No Known Activations