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

    Neuronpedia

    INDEX
    Explanations

    healthcare, assistant, lm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    缁
    0.46
    Cheap
    0.45
    Pel
    0.40
    ذهب
    0.39
    ද්ධ
    0.39
     పోటీ
    0.39
    IDING
    0.38
     beatae
    0.38
    팀
    0.38
    Weak
    0.38
    POSITIVE LOGITS
     erreicht
    0.42
    ванта
    0.37
     erreichte
    0.37
     Connection
    0.36
     pung
    0.35
     спа
    0.35
    arctan
    0.35
     gesehen
    0.35
     Запа
    0.34
    truncate
    0.34
    Act Density 0.000%

    No Known Activations