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

    Neuronpedia

    INDEX
    Explanations

    Descriptions of objects/people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ientos
    -0.07
     chicks
    -0.06
    edium
    -0.06
    lerde
    -0.06
     condoms
    -0.06
     nuevo
    -0.06
     discret
    -0.06
    ensible
    -0.06
    Uint
    -0.06
    loc
    -0.06
    POSITIVE LOGITS
     london
    0.07
    .Linq
    0.07
    .Compute
    0.06
     TObject
    0.06
    سام
    0.06
     adopts
    0.06
    Shipping
    0.06
    /fa
    0.06
     Deborah
    0.06
     alike
    0.06
    Act Density 0.101%

    No Known Activations