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

    Neuronpedia

    INDEX
    Explanations

    men

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urnd
    0.65
    ain
    0.62
    擔
    0.59
    odoc
    0.59
    eem
    0.59
    గొ
    0.58
    plex
    0.58
    ުރު
    0.57
     pity
    0.57
     piena
    0.56
    POSITIVE LOGITS
    haj
    0.73
    теп
    0.71
     vandalism
    0.70
     layer
    0.65
     เสร็จ
    0.65
    quela
    0.65
     బిల్
    0.65
     aufge
    0.65
    iosas
    0.65
    raintree
    0.64
    Act Density 0.005%

    No Known Activations