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

    Neuronpedia

    INDEX
    Explanations

    collecting destinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transdu
    0.41
     Lieu
    0.40
    和社会
    0.40
     Minority
    0.40
    স্ক
    0.39
    कृष्ट
    0.39
     Patrimonio
    0.39
    wireless
    0.39
    年前
    0.38
    śc
    0.38
    POSITIVE LOGITS
     Destination
    0.44
     destination
    0.42
    dest
    0.41
     Collect
    0.39
    Dest
    0.39
     anagram
    0.39
     poor
    0.39
    tasks
    0.39
    AA
    0.38
    PEL
    0.38
    Act Density 0.001%

    No Known Activations