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

    Neuronpedia

    INDEX
    Explanations

    data processing and metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aschen
    0.38
     কাছাকাছি
    0.38
    asida
    0.38
    lisi
    0.38
    müşt
    0.38
    ลา
    0.37
     Holton
    0.37
    ઊ
    0.36
    oglou
    0.35
     ॥
    0.35
    POSITIVE LOGITS
     processes
    0.42
     Processes
    0.42
     denominated
    0.38
    гада
    0.36
    processes
    0.35
     Prozesse
    0.34
     nefarious
    0.34
     procesos
    0.34
     denominations
    0.34
     denomination
    0.34
    Act Density 0.004%

    No Known Activations