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

    Neuronpedia

    INDEX
    Explanations

    reported/described

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aufgebaut
    0.42
    Changed
    0.41
     Managed
    0.39
     Created
    0.38
    に取り組
    0.38
    Created
    0.38
    Managed
    0.37
    Designed
    0.37
    Executed
    0.37
    Worked
    0.37
    POSITIVE LOGITS
     cited
    0.61
     featured
    0.60
     listed
    0.59
     reported
    0.54
     mentioned
    0.52
     posted
    0.47
     erroneously
    0.46
     noted
    0.46
     touted
    0.46
     described
    0.46
    Act Density 0.430%

    No Known Activations