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

    Neuronpedia

    INDEX
    Explanations

    social change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ことを
    1.19
    hitungan
    1.16
    ज़ी
    1.15
     octubre
    1.10
    ﺮ
    1.10
    çok
    1.09
     hebat
    1.09
     συνεχ
    1.08
     don
    1.06
    ीकृत
    1.05
    POSITIVE LOGITS
    t
    1.43
    ter
    1.38
    b
    1.33
    й
    1.29
     CREATE
    1.22
    is
    1.19
    ून
    1.17
    т
    1.16
    ल
    1.16
    ू
    1.15
    Act Density 0.001%

    No Known Activations