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

    Neuronpedia

    INDEX
    Explanations

    autonomous vehicles and robotics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initial
    0.45
     ran
    0.40
     Evidence
    0.40
     wanted
    0.39
     পারা
    0.39
     random
    0.39
     Puente
    0.39
     Pointer
    0.39
     pointer
    0.38
     Parole
    0.38
    POSITIVE LOGITS
    今
    0.44
    0.43
     desenvol
    0.42
    톰
    0.41
    Chrome
    0.40
    ніх
    0.40
    celand
    0.39
     удоволь
    0.38
    DESIGN
    0.38
    StoredKeys
    0.38
    Act Density 0.001%

    No Known Activations