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

    Neuronpedia

    INDEX
    Explanations

    Question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ้เก
    -0.06
     Uganda
    -0.06
    angles
    -0.06
    degree
    -0.06
    anti
    -0.06
    justify
    -0.06
    yal
    -0.06
     prova
    -0.06
    hatt
    -0.06
     वस
    -0.06
    POSITIVE LOGITS
     Poverty
    0.07
    のに
    0.07
     DD
    0.06
    %%%%%%%%%%%%%%%%
    0.06
    ΥΡ
    0.06
     hydrated
    0.06
     Philadelphia
    0.06
     apar
    0.06
    bring
    0.06
     semiclass
    0.06
    Act Density 0.010%

    No Known Activations