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

    Neuronpedia

    INDEX
    Explanations

    chemical concentrations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     krist
    -0.07
    cap
    -0.07
     трав
    -0.07
     Lifetime
    -0.07
    化石
    -0.06
    Silver
    -0.06
    .handleChange
    -0.06
    OLLOW
    -0.06
     brick
    -0.06
     trader
    -0.06
    POSITIVE LOGITS
     uomini
    0.07
     فهو
    0.07
    手中的
    0.07
    _constant
    0.07
    .byId
    0.06
     Korean
    0.06
    眼中
    0.06
     مق
    0.06
     encounters
    0.06
    .generator
    0.06
    Act Density 0.031%

    No Known Activations