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

    Neuronpedia

    INDEX
    Explanations

    model description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     microscopy
    0.41
    סי
    0.41
    生
    0.39
     wholesome
    0.38
    LM
    0.38
    Radiation
    0.37
    ЛИ
    0.37
    various
    0.37
    UI
    0.37
     космо
    0.37
    POSITIVE LOGITS
     întreb
    0.43
     Dieses
    0.38
    വരുടെ
    0.38
     ain
    0.36
     бясплат
    0.36
     ongeveer
    0.36
     wouldn
    0.36
     certes
    0.35
    腼
    0.34
    ophon
    0.34
    Act Density 0.001%

    No Known Activations