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

    Neuronpedia

    INDEX
    Explanations

    describing qualities and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.51
    ueil
    0.48
    ocal
    0.48
    xs
    0.47
    ison
    0.47
    iam
    0.45
    aning
    0.44
    vue
    0.44
    ẹo
    0.44
    kDa
    0.43
    POSITIVE LOGITS
    人
    0.49
     verke
    0.48
    يي
    0.46
     lép
    0.44
    毎
    0.44
    서는
    0.43
     efficace
    0.43
     finances
    0.43
     metropolis
    0.43
    PED
    0.43
    Act Density 0.000%

    No Known Activations